Articulating Reasons: An Introduction to Inferentialism

Reference: Brandom, R. B. (2000). Articulating Reasons: An Introduction to Inferentialism. Harvard University Press. Based on the 1998 Locke Lectures (Oxford). URL · SEP entry on inferentialism

Summary

Articulating Reasons is the compact entry point to Brandom’s inferentialist programme — a semantics without minds in which the meaning of a sentence is its role in the inferential practices of a community of speakers, rather than a mental representation of how things stand or a Tarskian truth-condition fixed by reference. Where representationalism takes reference and truth as basic and explains inference downstream, Brandom inverts the order: the basic semantic fact is which moves count as good reasons for which other moves, and reference, truth, and propositional content are explained as features of discursive practice downstream of inferential articulation. The slogan is meaning is use, descended from Wittgenstein and Sellars, but Brandom upgrades it from a regulative idea into a worked-out pragmatist semantics.

The mechanism is a deontic scorekeeping account of assertion. To assert something is to undertake a commitment and to license other speakers to attribute that commitment back; the score every speaker keeps on every other is a record of which commitments are undertaken, which are licensed, and which are incompatible. The content of a claim is then exhaustively determined by the inferential articulation of those commitment relations: what entitles you to claim it, what it entitles you to claim, what claims it is incompatible with. The book unfolds this through six lectures — Toward an Inferentialist Semantics, Action / Reason / Inference, Insights and Blindspots of Reliabilism, What Are Singular Terms?, A Social Route from Reasoning to Representing, and Objectivity and the Normative Fine Structure of Rationality — extracting the spine of the 700-page Making It Explicit in a form readable in a week. The view explicitly avoids smuggling in mentalism: there are no beliefs or intentions in the foundations, only the public, trace-checkable practice of giving and asking for reasons.

For agent communication, inferentialism is the philosophical underwriting of the public-semantics programme: it shows that you can have a full theory of meaning — not just a thin behavioural sketch — without ever quantifying over mental states. Singh’s critique of FIPA-style mentalism gestures at this; Brandom delivers the goods. The natural pairing in this vault is with CBCL and the commitment-based semantics of Singh, Fornara, and Colombetti, all of which can be read as engineering realisations of Brandom’s deontic scorekeeping at wire-format granularity.

Key Ideas

Inferentialism: meaning is fixed by inferential role — what claims entitle a speaker to make, what they exclude, what claims entitle the speaker to make them — not by reference or truth-conditions, which are explained downstream.
Deontic scorekeeping: a speaker’s discursive score is the record of which commitments they have undertaken, which entitlements they have, and which incompatibilities apply. Assertion = undertaking a commitment + licensing attribution back to oneself.
Material vs formal inference: inferences like “Pittsburgh is west of Princeton, therefore Princeton is east of Pittsburgh” are materially good — their goodness is part of the meaning of west and east, not a downstream consequence of logical form plus reference.
Logical vocabulary is expressive, not constitutive: connectives like “if … then …” let speakers make explicit, in the form of claims, inferential commitments that were previously only implicit in practice. Logic is the technology for making practices explicit, not the foundation.
Sapience vs sentience: what distinguishes language-users from thermostats is participation in the game of giving and asking for reasons. No phenomenology required.
Singular terms and objectivity from social structure: even reference and the objectivity of claims (the gap between “what we take to be correct” and “what is correct”) are recovered from the structure of perspectival scorekeeping rather than imported as primitives.
Anti-representationalist but not anti-realist: inferentialism is compatible with robust truth, reference, and a mind-independent world — it just refuses to take those as semantic ground floor.

Connections

Conceptual Contribution

Claim: A complete theory of linguistic meaning can — and should — be built from the publicly observable practice of giving and asking for reasons, with no mental states (beliefs, intentions) in the foundations. Reference and truth are downstream of inferential articulation, not upstream of it.
Mechanism: Deontic scorekeeping: every participant in discourse maintains a score on every other participant tracking which commitments they have undertaken, which entitlements they hold, and which incompatibilities are in play. The content of a sentence is exhaustively given by its inferential articulation in this scorekeeping practice — what entitles you to assert it, what asserting it entitles you to, and what asserting it is incompatible with. Logical vocabulary is a downstream expressive layer that lets implicit inferential commitments be made explicit as further claims.
Concepts introduced/used: Inferentialism, Material Inference, Deontic Scorekeeping, Discursive Practice, Commitment (Brandom), Entitlement (Brandom), Incompatibility (Brandom), Sapience vs Sentience, Expressive Role of Logic, Semantics-Without-Minds.
Stance: foundational philosophical monograph / lecture series.
Relates to: The direct philosophical underwriting of the public-semantics / commitment-based line in agent communication: Brandom shows you can have a full theory of meaning — not just a thin behavioural sketch — without invoking mental states, which is precisely what Singh needs and what Cohen and Levesque’s mentalistic ACL semantics could not deliver. CBCL and the commitment-machine tradition can be read as engineering realisations of deontic scorekeeping at wire-format granularity: a CBCL trace is a deontic score, and a dialect contract names which inferential moves are licensed. Genealogically the book is the late chapter of the Wittgenstein / Sellars / Quine line; the Myth of the Given (Sellars) is the move that lets meaning bypass preconceptual reference, and Brandom shows how far that move actually carries.

Tags

#inferentialism #philosophy-of-language #public-semantics #brandom #deontic-scorekeeping #foundations #pragmatism #commitment

Backlinks

Linked Pages

Myth of the Given

Sellars’s name (in EPM 1956) for the foundationalist idea — common across British empiricism, sense-datum theory, phenomenology, and parts of analytic epistemology — that knowledge must rest on a foundation of preconceptual sensory contents (the “given”) that are both non-inferentially known and epistemically authoritative. Sellars argues the picture is incoherent: anything that can serve to justify a belief is already conceptually articulated, and so cannot be preconceptual. Epistemic standing lives in the Space of Reasons, not in a layer of bare data outside it. The argument is the historical hinge of the inferentialist turn — the move that makes Semantics-Without-Minds philosophically defensible by foreclosing the alternative of grounding meaning in pre-discursive mental content.

In this vault

Two Dogmas of Empiricism - Quine

Two Dogmas of Empiricism

Reference: Quine, W. V. O. (1951). Two Dogmas of Empiricism. The Philosophical Review 60(1): 20–43. Reprinted in From a Logical Point of View (Harvard UP 1953). URL (PDF) · SEP entry on Quine

Summary

“Two Dogmas of Empiricism” is the paper that ended logical empiricism and made semantic holism respectable. Quine attacks two interlocking commitments of the Carnapian programme: (1) the analytic–synthetic distinction, the doctrine that some truths are true purely in virtue of meaning (analytic: all bachelors are unmarried) and others true in virtue of meaning plus how the world is (synthetic: snow is white); and (2) reductionism, the doctrine that every meaningful sentence is translatable into a statement about immediate experience. The two dogmas are mutually supporting — if either were good, the other would be needed to support it — and Quine shows that neither survives independent scrutiny.

The argument against the analytic–synthetic distinction works by demonstrating that every proposed definition of analyticity (in terms of synonymy, definition, semantic rules, or interchangeability salva veritate) either is circular or relies on a notion (cognitive synonymy, semantic rule) that is itself in need of the very explanation analyticity was supposed to provide. The argument against reductionism is that individual statements do not have their own range of experiential consequences — they face the tribunal of experience only as a body. The positive thesis that emerges is semantic holism: “Our statements about the external world face the tribunal of sense experience not individually but only as a corporate body” (§5). Coupled with Quine’s observation that no statement is immune to revision, this yields the famous web-of-belief picture: science is a fabric of beliefs in which the periphery is more responsive to experience and the interior (logic, mathematics, ontology) more conservative, but no part is constitutively immune.

For the inferentialist line, Quine plays an ambivalent role: he motivates inferentialism by demolishing the analytic–synthetic distinction, since one can no longer separate “the meaning of vixen” from “what we believe about vixens” — all the inferential connections in which vixen is enmeshed are partly constitutive of its meaning. But the same move threatens inferentialism, because if meaning is all the inferential connections then meaning is so holistic that no two speakers (or no speaker at two times) ever quite mean the same thing. This is the basis of Fodor and Lepore’s challenge: inferentialism inherits Quine’s holism, and Quine’s holism may be too much holism. For the ACL line, Quine matters because it implies that the meaning of propose, commit, retract in an ACL is constituted by the whole web of inferences in which those tokens are enmeshed — which is exactly why dialect contracts and protocol scaffolding matter: they fix the local web within which the wire-format performatives have determinate content.

Key Ideas

Two dogmas demolished: (1) the analytic–synthetic distinction is not defensible; (2) reductionism (every sentence has its own experiential cash value) is not defensible. They prop each other up; neither survives independently.
Circle of intensional notions: synonymy, analyticity, semantic rule, definition, cognitive equivalence — every attempt to define one in terms of the others is circular or empty.
Confirmation holism: scientific theories are tested as wholes against experience; the unit of empirical significance is the whole web of belief, not the individual sentence.
No statement is immune to revision: even logical and mathematical truths can be revised under sufficient empirical pressure (Quine cites quantum logic as illustration), and even peripheral observations can be saved by adjusting the interior of the web.
Web of belief: science is a fabric of beliefs with relations of mutual support; the periphery touches experience, the interior is more theoretically loaded, but the distinction is one of degree.
Pragmatic / empiricist reconstruction of analyticity: insofar as analytic has any use, it picks out sentences near the centre of the web, ones we are very reluctant to revise — a graded, pragmatic status rather than a sharp logical kind.

Connections

Conceptual Contribution

Claim: The analytic–synthetic distinction is undefendable, and theories meet the tribunal of experience as a whole, not statement-by-statement. Meaning is therefore not isolable from theory: the meaning of a term is partly constituted by the web of inferences in which it figures.
Mechanism: A six-section paper. §§1–4 walk through five candidate definitions of analyticity (definition, interchangeability salva veritate, semantic rules, etc.) and show each is either circular or empty. §5 attacks reductionism by showing that individual statements lack their own range of experiential consequences. §6 develops the positive picture: the web of belief / fabric of science, with peripheral statements more directly answerable to experience but no statement constitutively immune to revision.
Concepts introduced/used: Semantic Holism, Confirmation Holism, Web of Belief, Analytic-Synthetic Distinction, Quine-Duhem Thesis, Translation Manual (anticipating Word and Object).
Stance: foundational philosophical paper.
Relates to: Quine is the enabling condition for inferentialism: if the analytic–synthetic distinction held, then inferential role would only fix the analytic fragment of meaning and we would need reference / truth-conditions to do the rest. Quine collapses the distinction and lets inferentialism reach further. But Quine is also a threat: if meaning is the whole web, no two speakers mean the same thing, which is Fodor and Lepore’s pressure point against Brandom. The same dialectic applies to ACL semantics: meaning of a performative depends on the inferential web — which is why CBCL’s dialect contracts and the commitment-machine tradition matter — they fix the local web within which wire-format moves have determinate content. The complementary moves in the same period are Sellars 1956 (no Given) and Wittgenstein 1953 (meaning as use).

Empiricism and the Philosophy of Mind - Sellars

Empiricism and the Philosophy of Mind

Reference: Sellars, W. (1956). Empiricism and the Philosophy of Mind. In Feigl & Scriven (eds.), The Foundations of Science and the Concepts of Psychology and Psychoanalysis (Minnesota Studies in the Philosophy of Science, vol. I, pp. 253–329). University of Minnesota Press. Reissued as a standalone book in 1997 with study guide by Brandom. URL (Ditext transcription) · SEP: Sellars

Summary

Sellars’s Empiricism and the Philosophy of Mind — often known by the abbreviation EPM — is the founding text of the Pittsburgh school of philosophy (Sellars, Brandom, McDowell) and the source of the move that makes semantics without minds possible. The paper’s central target is the Myth of the Given: the idea that knowledge must rest on a foundation of preconceptual, given sensory contents (sense data, qualia, immediate awareness) which are both non-inferential and epistemically authoritative. Sellars argues that this picture is incoherent: anything that could be epistemically authoritative — anything that could justify a belief — must already be conceptually articulated, and so cannot be preconceptual. There is no epistemic free lunch at the periphery; all knowledge lives inside the space of reasons.

The argument unfolds across sixteen sections. The early sections deconstruct sense-datum theory; the middle sections develop Sellars’s positive account of looking-talk (looks-red is parasitic on is-red, not the other way around); the late sections develop the famous Jonesean myth in which thoughts and inner episodes are introduced as theoretical posits modelled on overt speech, with sensory impressions as further theoretical posits modelled on the perceptible properties of physical objects. The Jonesean myth is Sellars’s positive reconstruction of mentalistic talk: mental states are not pre-given inner objects we somehow inspect, but theoretical entities whose semantic content is fixed by their inferential role — which means mentalistic vocabulary is parasitic on public language, not foundational for it. This single move — “the categories of inner episodes are modelled on the categories of intersubjectively available language” — is the historical hinge on which the inferentialist turn rotates.

For agent communication, EPM is the philosophical warrant for treating the wire as the semantic ground floor and the agent’s mind as a downstream theoretical posit. The standard worry about public-semantics ACLs is that they leave out “what the agent really meant”; Sellars’s answer is that “what the agent really meant” is itself a theoretical extrapolation from public discursive practice, not a pre-given inner episode the public practice approximates. The mentalistic ACL semantics that Sellars’s argument undermines is precisely the FIPA/Cohen–Levesque picture that Singh 1998 sets aside.

Key Ideas

The Myth of the Given: the foundationalist idea that knowledge rests on preconceptual, immediately-known sensory contents is incoherent. Anything that can justify a belief is already conceptually articulated; epistemic standing lives in the space of reasons.
Looks-talk is parasitic on is-talk: “X looks red to me” is not a more secure foundation than “X is red”; it is a hedge introduced after we have learned to deploy is-red, used when we want to undertake the commitment to a colour-impression without undertaking the commitment to the colour itself.
The Jonesean myth: a methodological fiction in which a community with only behavioural language develops mentalistic vocabulary by introducing thoughts (modelled on overt speech) and sensations (modelled on the perceptible properties of physical objects) as theoretical entities. The point: mentalistic talk is a theoretical posit, not a description of pre-given inner data.
The space of reasons: “In characterizing an episode or a state as that of knowing, we are not giving an empirical description of that episode or state; we are placing it in the logical space of reasons, of justifying and being able to justify what one says.” §36 — the most-quoted line in 20th-century epistemology.
Psychological nominalism: all awareness of universals, kinds, sorts, and resemblances is linguistic awareness — there is no preconceptual awareness of abstract entities.
Sapience over sentience: the distinction between concept-using creatures and others is participation in the game of reasons, not the having of qualia.

Connections

Conceptual Contribution

Claim: Knowledge cannot be grounded in preconceptual given sensory contents; epistemic standing requires conceptual articulation, which is inherently a public, language-involving achievement. Mentalistic vocabulary is a theoretical posit modelled on public discourse, not a description of pre-given inner data.
Mechanism: A dialectical demolition of sense-datum theory in §§1–7, a developmental account of looks-talk in §§10–20, and the Jonesean myth in §§48–63 in which mentalistic vocabulary is introduced into a behavioural community as a theory whose entities (thoughts, sensations) are modelled on already-public categories (overt speech, perceptible properties).
Concepts introduced/used: Myth of the Given, Space of Reasons, Psychological Nominalism, Sapience vs Sentience, Looking-Talk, Jonesean Myth, Theoretical Posit, Conceptual Articulation, Semantics-Without-Minds.
Stance: foundational philosophical paper.
Relates to: The historical hinge on which the entire inferentialist / Pittsburgh school turns. Brandom and MIE are the systematic development of the positive programme implicit in EPM’s negative demolition. The argument that mentalistic talk is parasitic on public language is the philosophical underwriting of Singh’s move from mentalistic to social-commitment semantics for ACLs, and of CBCL’s decision to ground meaning at the wire format rather than at the agent internals. The complementary moves in the same generation are Quine 1951 (against the analytic-synthetic distinction and for holism) and Wittgenstein 1953 (meaning as use).

Philosophical Investigations - Wittgenstein

Philosophical Investigations

Reference: Wittgenstein, L. (1953). Philosophical Investigations. G. E. M. Anscombe (trans.). Blackwell, Oxford. Posthumous; Part I completed ca. 1945, Part II ca. 1949. URL (Anscombe translation PDF) · SEP entry · SEP: meaning

Summary

Philosophical Investigations (PI) is the grandparent of every twentieth-century approach to meaning that ties content to practice rather than to mental representation or correspondence — including the inferentialist, pragmatist, public-semantics, and commitment-based lines that this vault tracks. The book is non-systematic by design: §1–§133 set the stage by repudiating the Tractatus picture of language as a one-to-one mapping between names and objects; §§143–242 develop the rule-following considerations that culminate in the private-language argument (§243 ff.); the rest is a montage of “language-games” — concrete linguistic practices considered as wholes, in their natural settings — through which Wittgenstein dissolves rather than answers the standard puzzles of philosophy of mind and language.

Three Wittgensteinian theses are load-bearing for the rest of the vault. (1) Meaning is use (§43): “For a large class of cases — though not for all — in which we employ the word ‘meaning’ it can be defined thus: the meaning of a word is its use in the language.” Meaning is not a private mental object an inner Cartesian eye inspects, but a public regularity in linguistic practice. (2) Language-games are the unit of semantic analysis: a language-game is a complete, situated practice (giving orders, reporting events, asking questions, telling a joke, praying) within which words have determinate use. There is no language in general, only language-games. (3) The rule-following considerations and private-language argument: rules cannot determine their own application — there is no fact about how to “go on” in a series that is fixed independently of the practice of going on. Whether a person is following a rule correctly is settled by the public practice of the community, not by an inner state of intending-this-rule. A fortiori there can be no purely private language: meaning requires the corrective pressure of a community.

For agent communication, Wittgenstein is the ancestor in three respects. First, he supplies the philosophical permission to treat the wire — the publicly observable linguistic practice — as the semantic primary unit rather than as a thin trace of richer inner episodes. Second, the language-game concept directly anticipates the operational language-game tradition of Steels and the broader emergent-communication line. Third, the rule-following considerations are the philosophical complement to Lewis 1969 on convention: the question “what makes this regularity the rule the community follows?” is answered by the same mutual-expectation structure Lewis formalises and that Halpern–Moses 1990 reuse in distributed systems. The PI is also, importantly, the text Sellars and Brandom are explicitly working out the consequences of.

Key Ideas

Meaning is use (§43): the meaning of a word is its role in a public linguistic practice, not a mental object the speaker associates with the word.
Language-games: the unit of semantic analysis is not the isolated word, sentence, or proposition but the language-game — a complete situated linguistic practice (giving orders, reporting events, asking questions). There is no language in general; only language-games.
Family resemblance (§§65–67): concepts (like game) need not share a single essence; the items falling under a concept are connected by a network of overlapping similarities, like the resemblances among members of a family.
Rule-following considerations (§§143–242): rules do not determine their own application; what counts as “going on in the same way” is settled by the public practice of the community, not by an inner state of intending-the-rule.
Private-language argument (§243 ff.): a language whose terms refer to inherently private sensations, with no public criteria of application, is not a possible language. Meaning requires correction by a community.
Forms of life (Lebensformen): language-games are embedded in broader patterns of activity and shared natural history; meaning is ultimately answerable to these patterns rather than to abstract logical structure.
Philosophy as therapy: many traditional philosophical problems arise from misuse of language and dissolve when we attend to the actual language-games in which the relevant words have their home.

Connections

Conceptual Contribution

Claim: Linguistic meaning is constituted by use — the role of expressions in concrete, situated language-games sustained by a community — not by inner mental content, abstract logical structure, or correspondence to extra-linguistic facts. Rules do not determine their own application; the public practice of the community does.
Mechanism: A montage of detailed cases (the builder’s language-game §2, slabs and pillars §§19–20, the diary-keeper in §258) in which traditional philosophical pictures of meaning, reference, sensation, and rule-following are shown to misfire when applied to actual linguistic practice. The private-language argument (§243 ff.) blocks the move to inner ostensive definition; the rule-following considerations (§§143–242) block the move to rules that determine their own application.
Concepts introduced/used: Meaning As Use, Language Game, Form of Life, Family Resemblance, Rule-Following, Private Language Argument, Public Criterion, Aspect Perception, Philosophical Therapy.
Stance: foundational philosophical work / posthumous opus magnum.
Relates to: The grandparent of every meaning-as-use approach in the twentieth century — Sellars explicitly takes up the public-language-priority thesis, Quine generalises the rejection of pre-linguistic semantic facts, and Brandom and Articulating Reasons develop the systematic inferentialist account that the PI’s aphoristic style only gestures at. The language-game idea is the direct ancestor of Steels’ operational language-games and the broader emergent-communication tradition. The rule-following considerations complement Lewis 1969 on convention: where Lewis gives a game-theoretic answer to “what sustains this regularity?”, Wittgenstein gives a practice-theoretic answer to “what makes it a rule rather than a regularity?” — these two answers operate at the same conceptual layer.

Commitment Machines - Yolum and Singh

Commitment Machines

Reference: Yolum, P. & Singh, M.P. (2002). Intelligent Agents VIII: Agent Theories, Architectures, and Languages (ATAL-01), LNAI 2333, pp. 235–247. Springer. (A preliminary version appeared in WET-ICE 2000.) Source file: yolum-singh-2002-commitment-machines.pdf. URL

Summary

Yolum and Singh propose commitment machines (CMs) as a protocol formalism that, unlike finite-state machines or Petri nets, attaches declarative meaning to states and actions in terms of the participants’ Social Commitments. A CM is a triple ⟨M, Δ, F⟩ of a finite minimal set of meanings (formulas in a propositional language extended with a commitment operator Cₓp and a strict-implication operator ;), a set of actions ⟨a : e⟩ whose effect e is itself a meaning, and a set of consistent final meanings. Transitions are not enumerated — they are inferred from the logical consequences of applying an action’s effect to the current meaning. The running example is the NetBill Protocol, specified by atomic propositions (request, goods, pay, receipt) and abbreviations for conditional commitments (accept = C_c(goods ; pay), promiseGoods = C_m(accept ; goods), etc.); three reasoning rules govern how commitments evolve as content propositions are made true.

The paper’s central technical contribution is a compilation procedure that turns any complete CM (one whose meaning set is closed under antecedence) into a deterministic FSM that can be executed in constant space without commitment reasoning at run time. The procedure is shown sound (Theorem 2 — every realised computation is generated by the source CM) and complete (Theorem 3 — every CM-generated computation has a semantically-strongest, efficient FSM-realised counterpart from true), via a chain of lemmas about semantic superiority, efficient computations, and endpoint equivalence. Because the meanings of states are explicit, agents executing the CM directly can plan paths through the protocol that exploit opportunities (e.g. a merchant proactively quoting without a request, “try before you buy” deals) and handle exceptions, recovering autonomy that pure-token FSM/Petri-net specifications eliminate.

Key Ideas

Commitment machine ⟨M, Δ, F⟩: state space is a finite minimal set of meanings (formulas) rather than tokens; actions ⟨a : e⟩ carry effect-meanings; final states are a consistent subset of meanings.
Inferred transitions: q ⊨_⟨a:e⟩ r iff (q ∧ e) ⊢ r — transitions are derived from logical entailment, not enumerated edges.
No fixed start state: a CM has no s₀; participants may begin from any meaning whose commitments they accept (typically true).
Three reasoning rules over commitments: (1) Cₓp discharges when p holds; (2) Cₓ(p ; r) collapses to base-level Cₓr when p holds; (3) Cₓ(p ; r) ceases when r holds before p, with no new commitment.
Compilation to deterministic FSM under two restrictions: (R1) no transition mᵢ → mⱼ if mᵢ ⊢ mⱼ (no information-free moves); (R2) the target meaning must dominate all alternatives entailed by the action (forcing maximal information).
Completeness requires “complete” CMs — meaning set closed under antecedence — so that a unique strongest target meaning always exists; trivially achieved by closing under conjunction.
Soundness, completeness, determinism established as theorems over the computation abstraction (sequences of meanings interleaved with actions); computations are compared by semantic superiority and endpoint equivalence rather than literal action-sequence equality.
Flexibility recovered for free: since states encode meanings, agents can skip steps, reorder, or take unsolicited shortcuts whenever the resulting meaning is still in M and the path to a final meaning still exists.

Connections

Conceptual Contribution

Claim: Multi-agent protocols should be specified by giving states and actions declarative meaning in terms of the participants’ commitments — not by enumerating legal token sequences — and any such specification can be soundly and completely compiled to a deterministic FSM, recovering executability without forfeiting flexibility, autonomy, or the ability to handle exceptions and exploit opportunities.
Mechanism: A propositional language with a commitment operator Cₓ and strict-implication ;; meaning sets M and final-meaning sets F (consistent w.r.t. logical consequence); action effects given as meanings; transitions inferred via (q ∧ e) ⊢ r. Compilation Procedure 1 maps ⟨M, Δ, F⟩ → ⟨S=M, Σ={a}, s₀=true, Q=F, δ⟩ under the two information-monotonicity restrictions; Procedure 2 promotes a computation to its semantically strongest counterpart, Procedure 3 removes redundant self-transitions, yielding efficient semantically-strongest computations that are realised by the compiled FSM. Soundness (Thm 2), determinism (Thm 1), and completeness for complete CMs (Thm 3) are proved.
Concepts introduced/used: Commitment Machines, Commitment-Based Protocol, Commitment-based Semantics, Conditional Commitment, Social Commitment, Public Semantics, Verifiable Semantics, NetBill Protocol, Endpoint Projection (structural analogue), Conversation Protocols, Speech Act Theory
Stance: formal-semantic / engineering
Relates to: Direct precursor and structural sibling of Flexible Protocol Specification and Execution (Yolum & Singh, AAMAS-02), which lifts the same six commitment operations (Create / Discharge / Cancel / Release / Assign / Delegate) into the Event Calculus and adds an abductive planner; ATAL-01 here is the FSM-compilation half of that programme. Companion to A Commitment-Based Approach to Agent Communication (Fornara & Colombetti, AAMAS-02 / AAI-04), which gives an OO/FSM operational semantics for the same primitives plus a precommitment state for directives. Carries forward the social-agency programme of ACL Rethinking Principles (Singh 1998) and answers Wooldridge’s challenge in Verifiable Semantics for ACLs by grounding meaning in publicly-observable commitment formulas rather than agent mental state. The Discussion explicitly contrasts with Smith et al.’s joint-intention–based protocols (mental constructs vs. social constructs) — the same fork that Intention Is Choice with Commitment anchors on the mental side. Structurally a direct analogue of choreographic Endpoint Projection: both compile a globally-specified protocol artefact to a per-role executable, the CM/FSM compilation losing declarative meaning for runtime efficiency much as endpoint projection loses the global view for distributable execution. This makes ATAL-01 the load-bearing reference for the constructive synthesis suggested in the Pact - A Choreographic Language for Agentic Ecosystems entry — choreographies could carry both communication structure (Pact-side) and a CM-style commitment trace (Singh-side), with one compilation step yielding both deadlock-freedom and conformance-checkability.

Tags

CBCL - Safe Self-Extending Agent Communication

CBCL: Safe Self-Extending Agent Communication

Reference: O’Connor, H. (2026). LangSec Workshop, IEEE Security and Privacy Workshops (SPW 2026). arXiv:2604.14512v1 [cs.CR], 16 Apr 2026. Source file: oconnor-cbcl-langsec26.pdf. URL. Reference implementation: https://codeberg.org/anuna/cbcl-rs.

Summary

Building on McCarthy’s 1975/1982 Common Business Communication Language vision and the language-theoretic security programme of Sassaman, Patterson, Bratus and Locasto (Security Applications Of Formal Language Theory), this paper presents a contemporary CBCL: an agent communication language designed so that all messages — including runtime language extensions — remain within the deterministic context-free (DCFL) complexity class. The motivating diagnosis is that contemporary agent communication has slid up the Chomsky hierarchy without acknowledging the security cost: KQML and FIPA-ACL are CFL with informal extensibility, but MCP and LLM-based agent frameworks operate over inputs whose effective complexity is recursively-enumerable, where the validity of an arbitrary message is undecidable and “weird machines” (Exploit Programming - From Buffer Overflows To Weird Machines) become unavoidable. CBCL takes the opposite tack: minimal core (8 performatives — tell, ask, reply, hello, bye, ok, error, cancel) plus a homoiconic dialect mechanism that lets agents define, transmit, and adopt domain-specific vocabularies as first-class CBCL messages, with three machine-checked safety invariants — R1 (no recursion in dialect templates), R2 (declared resource bounds on depth, expansion size, verification time), R3 (core-vocabulary preservation) — that together guarantee DCFL preservation under arbitrary finite sequences of dialect installations.

The paper accompanies the design with a Lean 4 formalization (≈5,400 lines, 16 modules, 176 machine-checked theorems, zero sorry gaps, no custom axioms) covering parser correctness (soundness + completeness), R1–R3 verification, pipeline totality, and the central dcfl_preserved closure theorem; a verified parser binary cbcl-parse is extracted from the proofs. A separately-developed Rust reference implementation (cbcl-rs, ≈11,000 lines, no_std-compatible core) ships a hand-rolled O(n) parser, dialect verification engine, gossip-based dialect propagation (O(log n) convergence per Demers et al.), C FFI/WASM bindings, property-based and differential tests, and cargo-fuzz targets; differential tests cross-validate the Rust parser against the Lean-extracted binary, eliminating spec-implementation parser differentials. Five example dialects (precision agriculture, AI planning, cross-chain asset transfer, artifact management, email) are R1–R3-verified end-to-end. A draft IETF Internet-Draft specifying application/cbcl and a Nostr transport binding (cbcl-nostr) accompany the paper. The Discussion explicitly aligns the design with Singh’s social-agency programme: dialect installation is treated as a public commitment to the dialect’s declared semantics — semantic divergence becomes a breach of commitment, observable and accountable, rather than a hidden failure of shared mental state — sidestepping the unverifiable mentalistic semantics critique of Verifiable Semantics for ACLs.

Implementation status (post-paper, cbcl-rs). The reference implementation has shipped two further safety invariants the paper sketches as future work, plus a richer Lean formalisation: R4 (Integrity) — Ed25519-style signatures over canonical encodings via an algorithm-agnostic Signer trait, with three-valued install verdicts (Valid / Unsigned / Invalid) — and R5 (Contract Well-formedness) — optional (protocol …) and (shape …) clauses on a dialect, expressing causal Merkle DAG protocols and per-performative shape contracts; R5 enforces acyclicity, reachability from begin, performative definedness with ancestor closure for extends, step uniqueness, and depth-bound respect, all decidable in linear fuel at install time. The §VII-D structural-contracts vision is therefore live (SPEC-002, SPEC-003): verify_monotone, verify_all_is_meet, and verify_eventually_consistent are proved theorems showing causal-protocol verification is a lattice homomorphism that joins coordination-free under G-Set store merge — explicit CALM Theorem alignment. The Lean codebase has grown to 380+ declarations across 19 files (still zero sorry, only the standard axioms propext / Classical.choice / Quot.sound); the workspace ships 837 tests including 584 cbcl-core unit tests, 37 proptest cases, 21 differential integration tests against the Lean-extracted binary, libFuzzer harnesses, and cargo-mutants mutation testing at a 90% kill threshold. The crate layout has grown from the paper’s five to seven: the original cbcl-core / cbcl-parser / cbcl-cli / cbcl-wasm / cbcl-ffi plus cbcl-erl (Erlang/LFE binding, SPEC-009 — with SPEC-010 binding-conformance suite) and cbcl-arena (Agent Arena platform, SPEC-012 — composable referee on cbcl-lfe-router with capability-keyed message routing and signed receipt logs). A worked sealed-bid auction dialect (SPEC-004) demonstrates structural defence against false-claim manipulation — concrete evidence that the R5 contract layer is rich enough to encode mechanism-design integrity properties decidably. The earlier Scheme prototype (anuna-research/cbcl) is superseded; architecture decisions live as ADRs under .hence/ (purity boundary, parser library choice, error handling, WASM API surface, R4 adversarial review).

Key Ideas

DCFL as the Goldilocks complexity class: Regular is too weak for nested envelopes/dialects; general CFL admits ambiguous grammars and parser-differential attacks; context-sensitive is PSPACE-complete; Type-0 is undecidable. DCFL is the minimal class that supports nested structure with class-level unambiguity (parser equivalence under language evolution).
Homoiconic self-extension: Dialect definitions are themselves valid CBCL messages, parsed by the same recogniser used for ordinary communication — a single attack surface, no separate meta-language. Inspired by Racket’s #lang mechanism.
Three safety invariants R1–R3: declarative pattern-template substitution only (no recursion, no iteration, no reflection); declared resource bounds (depth ≤ 64, expansion ≤ 8192 chars, verification ≤ 1000 ms); the eight core performatives cannot be redefined.
DCFL preservation theorem: dialect invocations must appear inside a (lang name …) wrapper; the lang tag plus a unique dialect name forms a prefix-free partition that lets a deterministic pushdown automaton dispatch to the appropriate subgrammar without extra lookahead — circumventing the fact that DCFLs are not closed under union in general. Mechanised in Lean 4 as dcfl_preserved.
Lean 4 formalization with extraction: 176 theorems, 0 sorry gaps, no custom axioms; the verified parser binary cbcl-parse is extracted from the proofs and runs the same fuel-bounded recursive-descent parser as the model.
Rust reference implementation: cbcl-core (no_std, no unsafe), cbcl-parser, cbcl-cli, cbcl-ffi, cbcl-wasm. Differential tests against the Lean-extracted binary; cargo-fuzz over five entry points.
Eight core performatives (tell, ask, reply, hello, bye, ok, error, cancel) plus four message categories (simple, meta, lang-scoped, wrapped); keyword parameters in Common-Lisp style (:thread, :in-reply-to).
Single-pass template expansion: terminates in time linear in the template plus argument size; not Turing-complete; output is not fed back into the expander, ruling out unbounded re-expansion.
Epidemic dialect propagation: gossip-based with Demers et al.’s O(log n) convergence bound; agents independently verify R1–R3 and signatures before installing.
Canonical serialization per RFC 9804 for cryptographic operations — deterministic byte representation as a precondition for signature verification.
Dialect identity by content hash: name collisions resolved by canonical-form hash; downgrade attacks rejected at installation.
Self-expression vs self-adaptation (Zambonelli et al.): traditional ACLs support only parameter tuning within fixed structure; CBCL is a self-expressive protocol whose vocabulary structurally evolves under safety constraints.
Singh-aligned reading of dialect installation: a public commitment to declared semantics, with :examples clauses providing machine-checkable behavioural anchors — semantic divergence as observable breach rather than hidden mental-state mismatch.
Stated limitations: DCFL ceiling means no recursive transformations, no cross-field references (e.g. checksums over fields), no aggregation over variable-length collections, no context-sensitive validation. Standish-taxonomy paraphrastic only — no Orthophrase, no Metaphrase. Trust infrastructure (key distribution, revocation) and dialect-curation policy left to deployment.
Structural-contracts extension (sketched in §VII-D, shipped post-paper as R4 + R5): Ed25519-style dialect signatures plus protocol constraints as causal Merkle DAGs over performative-typed messages, with Visibly Pushdown Languages for shape constraints and coordination-free monotonic verification over an append-only store. Lean-mechanised lattice-homomorphism theorems (verify_monotone, verify_all_is_meet, verify_eventually_consistent) establish that replica verdicts join under G-Set merge.

Connections

Common Business Communication Language — McCarthy’s 1975/1982 origin; CBCL is the formally-verified realisation of that vision.
Security Applications Of Formal Language Theory — Sassaman et al.’s LangSec foundations.
Proof-Carrying Code - Necula — Necula 1997, the architectural ancestor of CBCL’s R4 split (host runs a small certified verifier; producer ships the proof).
Enforceable Security Policies - Schneider — Schneider 2000, the formal warrant for R5 monotone-verdict trace monitoring.
An Axiomatic Basis for Computer Programming - Hoare — Hoare 1969, root of the contract-based verification line CBCL inherits.
Authentication in Distributed Systems - Lampson Abadi Burrows Wobber — Lampson et al. 1992, the Speaks-For Calculus for delegated commitments.
Articulating Reasons - Brandom — Brandom 2000, the philosophical underwriting of Public Semantics (entry point).
Making It Explicit - Brandom — Brandom 1994, the full inferentialist treatise.
Empiricism and the Philosophy of Mind - Sellars — Sellars 1956, the Myth of the Given that makes Semantics-Without-Minds possible.
Philosophical Investigations - Wittgenstein — Wittgenstein 1953, Meaning As Use / language-games / rule-following.
Two Dogmas of Empiricism - Quine — Quine 1951, Semantic Holism.
Assertion - Stalnaker — Stalnaker 1978, Common Ground update semantics — operational analogue of CBCL’s verdict ledger.
Languages and Language - Lewis — Lewis 1975, Convention of Truthfulness picture of how an abstract language gets in force in a population.
Communicative Actions for Artificial Agents - Cohen Levesque — Cohen & Levesque 1995, the Mentalistic Semantics high-water mark CBCL deliberately is not.
FIPA-ACL Specifications — the engineering of FIPA-ACL (envelope, conversation-id, ontology slot) CBCL inherits; the semantics it replaces.
An Ontology for Commitments in Multiagent Systems - Singh — Singh 1999, the formal commitment ontology CBCL’s dialect contracts instantiate.
Jones-Sergot Normative Systems — Jones & Sergot 1993, the Counts-As Relation that gives wire events institutional meaning under a dialect contract.
Exploit Programming - From Buffer Overflows To Weird Machines — weird-machine analysis CBCL is designed to preclude at the parser layer.
PKI Layer Cake - Kaminsky Patterson Sassaman — concrete parser-differential attacks; CBCL’s class-level unambiguity rules these out at the grammar level.
The Halting Problems of Network Stack Insecurity
A Language-Based Approach To Prevent DDoS
LangSec
KQML as an Agent Communication Language
KQML - A Language And Protocol For Knowledge And Information Exchange
FIPA-ACL
ACL Rethinking Principles — Singh’s social-agency critique that CBCL’s “dialect installation as public commitment” inherits.
Agent Communication Languages - Rethinking the Principles
Verifiable Semantics for ACLs
A Common Ontology Of ACLs
Commitment-based Semantics
The State of the Art in Agent Communication Languages
Trends in Agent Communication Language
Toward Principles for the Design of Ontologies Used for Knowledge Sharing — Gruber’s ontological-commitment principle CBCL inherits.
Some Philosophical Problems from the Standpoint of Artificial Intelligence — McCarthy & Hayes’s representation/computation separation.
Elephant 2000 - A Programming Language Based on Speech Acts — McCarthy’s intra-program speech-act counterpart to CBCL’s inter-organisational vision.
Adjectival Modifiers
S-expression
Homoiconicity
Code as Data
Creating Languages in Racket — Flatt’s #lang mechanism that inspired CBCL’s homoiconic self-extension.
Extensibility in Programming Language Design - Standish
Language Extensibility Taxonomy
Paraphrase
Orthophrase
Metaphrase
Self-Expression
Self-Adaptation Self-Expression Self-Awareness ASCENS
Dialects and Idiolects
Keeping CALM - When Distributed Consistency is Easy — CALM theorem underwriting the forthcoming coordination-free contracts extension.
Visibly Pushdown Languages
MCP Landscape Security Threats And Future Research Directions
Survey Of AI Agent Protocols
Survey Of Agent Interoperability Protocols
ClawWorm Self-Propagating Attacks Across LLM Agent Ecosystems — concrete LLM-agent worm whose root-cause analysis CBCL’s lang-scoped provenance addresses.
Why AI Agents Communicate In Human Language
Why Do Multi-Agent LLM Systems Fail
Gossiping in Distributed Systems
Gossip-based Aggregation in Large Dynamic Networks

Conceptual Contribution

Claim: Agent communication languages can be simultaneously expressive, runtime-extensible, and tractably verifiable iff every message — including those that extend the language — is constrained to the deterministic context-free language class; this constraint is compatible with first-class self-extension, can be machine-checked end-to-end, and converts the unverifiable-mental-state problem of mentalistic ACLs into a public-commitment problem at the protocol layer.
Mechanism: Eight-performative core grammar (LL(1), DCFL); homoiconic dialect mechanism — dialect definitions are valid CBCL messages with extend clauses describing pattern-template substitutions; three safety invariants R1–R3 enforced at installation (no recursion via DFS cycle detection, declared resource bounds, core-vocabulary preservation); (lang name …) wrapper providing prefix-free deterministic dispatch into per-dialect sub-grammars so the union remains DCFL. Lean 4 formalization (LeanCbcl, ~5,400 LoC, 176 theorems) covering parser soundness/completeness, R1–R3, pipeline totality, and dcfl_preserved; verified parser extracted to a runnable binary (cbcl-parse). Rust reference implementation (cbcl-rs, ~11,000 LoC) with a ResourceContext-tracked single-pass expander, gossip-based dialect propagation (O(log n) per Demers et al.), canonical RFC-9804 serialization for signing, algorithm-agnostic Signer trait, C FFI / WASM bindings, property-based + differential tests, fuzz targets. Draft IETF application/cbcl Internet-Draft and Nostr transport binding.
Concepts introduced/used: Deterministic Context-Free Language, LangSec, Homoiconicity, S-expression, Dialects and Idiolects, Performatives, Self-Expression, Paraphrase, Orthophrase, Metaphrase, Visibly Pushdown Languages, CALM Theorem, Commitment-based Semantics, Public Semantics, Verifiable Semantics, Adjectival Modifiers, Ontological Commitment, Lean 4, Property-Based Testing, Parser Differential Attack, Weird Machine, Gossip Protocols, Canonical Serialization, Nostr, hence
Stance: engineering / formal-methods, with explicit position-taking on the agent-communication design space
Relates to: Realises McCarthy’s Common Business Communication Language vision (1975/1982) by giving formal safety guarantees McCarthy could only gesture at. Sits squarely in the LangSec programme of Security Applications Of Formal Language Theory and Exploit Programming - From Buffer Overflows To Weird Machines, extending it from input-validation analysis to protocol design — claiming, plausibly, to be the first ACL designed from LangSec principles and the first to demonstrate that LangSec is compatible with runtime self-extension. Inherits the DCFL-vs-ambiguous-CFG argument from PKI Layer Cake - Kaminsky Patterson Sassaman and applies it at the message layer rather than the certificate layer. Builds explicitly on Singh’s social-agency critique (ACL Rethinking Principles) and Wooldridge’s verifiability programme (Verifiable Semantics for ACLs) by treating dialect installation as a public commitment whose semantics are anchored by the :examples clause — a machine-checkable analogue of the commitment-trace conformance that Flexible Protocol Specification and Execution (Yolum & Singh) and Commitment Machines - Yolum and Singh establish for protocol actions. Where Pact - A Choreographic Language for Agentic Ecosystems takes the individual-rationality fork to answer “why follow a protocol?”, CBCL takes the publicness/verifiability fork: the meaning of a message is fully determined by the formal grammar plus declared semantics, with no mental-state inference required. Inherits Gruber’s ontological-commitment architecture but replaces “out-of-band agreement” with in-protocol propose/query/teach. The extensibility design draws on Creating Languages in Racket (Flatt’s #lang) and respects the boundary set by Extensibility in Programming Language Design - Standish: paraphrastic only, deliberately excluding orthophrase/metaphrase to keep the attack surface bounded. The forthcoming structural-contracts extension uses Visibly Pushdown Languages for shape constraints and the CALM Theorem for coordination-free verification — a natural bridge to commitment-machine semantics. The LLM-agent threat-model framing (ClawWorm Self-Propagating Attacks Across LLM Agent Ecosystems, MCP Landscape Security Threats And Future Research Directions) positions CBCL as the structural alternative to MCP/JSON-RPC-with-natural-language: same extensibility, vastly tighter security envelope.

Cohen and Levesque

Philip R. Cohen and Hector J. Levesque, whose joint and individual work in the 1980s–1990s formalised intention, joint intention, and the rational-balance constraints on BDI-style agents. Their 1990 paper Intention Is Choice with Commitment (AIJ 42) is the canonical formal model of intention as a persistent goal — a commitment to maintain a goal until it is believed achieved, believed unachievable, or its motivating reason dissolves. Cohen & Levesque (1991) Teamwork extends the analysis to joint action and joint intentions in multi-agent settings.

In this vault

ACL Rethinking Principles

Agent Communication Languages: Rethinking the Principles

Reference: Munindar P. Singh (1998). IEEE Computer, December 1998, pp. 40-47. Source file: computer-acl-98.pdf. URL

Summary

Singh surveys the state of Agent Communication Languages (ACLs) such as KQML and FIPA/Arcol, and argues that their dominant mental-agency semantics (defining communicative acts in terms of beliefs and intentions) is conceptually unsatisfying and practically untestable because we cannot read agents’ minds. He proposes a conceptual shift to social agency: ACL semantics should be grounded in a public perspective on commitments, roles, and societies, so compliance with the standard is observable and testable.

The paper maps the ACL design space along two critical dimensions — meaning (perspective, type, basis, context, coverage of communicative acts) and agent construction (design vs. execution autonomy) — and shows how both KQML and Arcol emphasize private, mental-state semantics and thus fail to enable true heterogeneous interoperation. Singh’s alternative emphasizes protocols, roles, and “society management” infrastructure as a richer public substrate for ACLs.

Key Ideas

Mental-agency ACL semantics (KQML, Arcol, early FIPA) cannot be verified without inspecting agent internals.
ACLs need a public perspective, conventional meaning, pragmatics, and full coverage of communicative act categories.
Seven categories of communicative acts: assertives, directives, commissives, permissives, prohibitives, declaratives, expressives.
Social agency replaces BDI with commitments, roles, and societies as the semantic basis.
Dialects/idiolects arise when only private perspectives are considered.

Connections

FIPA-ACL
FIPA-ACL Specifications
KQML
Speech Act Theory
Agent Communication Languages
Multi-Agent Systems
Communicative Actions for Artificial Agents - Cohen Levesque — the Mentalistic Semantics high-water mark Singh is critiquing
An Ontology for Commitments in Multiagent Systems - Singh — Singh’s own formal sequel: the four-place commitment ontology
Commitment Machines - Yolum and Singh
A Commitment-Based Approach to Agent Communication
Articulating Reasons - Brandom — the philosophical underwriting of public, commitment-based semantics
Making It Explicit - Brandom
Jones-Sergot Normative Systems — Counts-As Relation for institutional grounding of commitments
CBCL - Safe Self-Extending Agent Communication — O’Connor 2026: contemporary realisation of Singh’s social-agency programme (dialect installation as public commitment) in a Lean-verified LangSec-grounded ACL.

Conceptual Contribution

Claim: Agent Communication Language semantics must abandon mental agency (beliefs/intentions) and be grounded in a public, social perspective (commitments, roles, societies) in order to be testable and support heterogeneous interoperation.
Mechanism: Surveys KQML, Arcol, FIPA; lays out a two-dimensional design space (meaning × agent construction); shows that mental-state semantics cannot determine compliance; proposes social-agency framework using protocols, roles, and “society management” infrastructure.
Concepts introduced/used: Mentalistic Semantics, Public Semantics, Social Agency, Commitments, Communicative Acts, Verifiable Semantics, Interoperability, Dialects and Idiolects
Stance: critique / foundational
Relates to: Direct antecedent to Verifiable Semantics for ACLs (Wooldridge) which formalises the verification problem Singh names. Sharpens the critique of the mentalistic approach underlying KQML Overview and FIPA-ACL, and motivates commitment-based frameworks such as Agent Communication And Institutional Reality.

Tags

Commitment-based Semantics

Approach that grounds ACL message meaning in public social commitments rather than private mental states — making conformance verifiable.

In this vault

ACL Rethinking Principles
Agent Communication Languages - Rethinking the Principles
Agent Communication And Institutional Reality
A Common Ontology Of ACLs
Public Semantics
Mentalistic Semantics
Flexible Protocol Specification and Execution
A Commitment-Based Approach to Agent Communication
CBCL - Safe Self-Extending Agent Communication — modern LangSec-grounded ACL inheriting Singh’s social-agency programme; dialect installation as public commitment

Public Semantics

ACL semantics grounded in externally observable facts (commitments, roles, institutional state) rather than private mental state.

In this vault

ACL Rethinking Principles
Agent Communication And Institutional Reality
Commitment-based Semantics
Mentalistic Semantics
CBCL - Safe Self-Extending Agent Communication — dialect installation as a public commitment

Semantics-Without-Minds

The position — descended from Wittgenstein / Sellars / Brandom — that a complete theory of linguistic meaning can be built from publicly observable practice without taking any mental state (belief, intention, desire, qualia) as semantic primitive. Sellars’s Myth of the Given argument blocks the move to pre-conceptual inner content; Wittgenstein’s rule-following considerations block the move to private semantic rules; Brandom’s Deontic Scorekeeping supplies the positive replacement. The position is the philosophical underwriting of the Public Semantics / Commitment-based Semantics programme in agent communication, and the cleanest answer to the worry that protocols built on observable commitments are “thin behavioural surrogates” for “real” mentalistic meaning. They are not — they are the foundation.

In this vault

Expressive Role of Logic

(page does not exist)

Sapience vs Sentience

Brandom / Pittsburgh-School distinction: sentience is the capacity for awareness (shared with non-linguistic animals), sapience is the capacity to play the game of giving and asking for reasons in the Space of Reasons. Only sapient beings have conceptual content.

In this vault

Incompatibility (Brandom)

Brandom’s modal-pragmatist primitive: two contents are incompatible iff commitment to one precludes entitlement to the other. Used in Between Saying and Doing to recover modal vocabulary from inferential structure.

In this vault

Entitlement (Brandom)

Brandom’s normative status complementing commitment: a speaker is entitled to a commitment when they have adequate reasons (perceptual, inferential, or testimonial) to undertake it.

In this vault

Commitment (Brandom)

Normative status attributed to a speaker by uttering an assertion in Discursive Practice: the speaker is committed to the asserted content and to its inferential consequences. Tracked alongside entitlement in the scorekeeping picture of Making It Explicit.

In this vault

Discursive Practice

Brandom’s term for the normative practice of giving and asking for reasons. Constitutes the Space of Reasons and is the medium in which commitments and entitlements are tracked.

In this vault

Deontic Scorekeeping

Brandom’s model of discursive practice: each speaker maintains a score on every other tracking which commitments that speaker has undertaken, which entitlements they hold, and which incompatibilities are in play. To assert is to undertake a commitment and license attribution back to oneself; the meaning of a sentence is exhaustively given by how its assertion changes the score. The model is the formal core of Inferentialism: it shows how an entire theory of meaning, including reference and objectivity, can be built from publicly observable normative bookkeeping with no recourse to mental states. Stalnaker’s Common Ground / Context Set update model of assertion and Hamblin-style commitment stores from formal dialectic are the two other canonical formal models of the same phenomenon.

In this vault

Articulating Reasons - Brandom
Making It Explicit - Brandom
Inferentialism
Material Inference
Semantics-Without-Minds
Assertion - Stalnaker — Common Ground update is the operational analogue
Common Ground
Fallacies - Hamblin — Commitment Store from formal dialectic
Commitment in Dialogue
An Ontology for Commitments in Multiagent Systems - Singh — ACL-side instantiation
A Commitment-Based Approach to Agent Communication
Commitment Machines - Yolum and Singh
Public Semantics
Commitment-based Semantics
CBCL - Safe Self-Extending Agent Communication

Material Inference

Sellars’s term, central to Brandomian inferentialism, for inferences whose goodness is part of the meaning of the constituent terms rather than a downstream consequence of logical form plus reference. The canonical example: Pittsburgh is west of Princeton therefore Princeton is east of Pittsburgh. The inference is not classically valid — its goodness depends on what west and east mean — but it is materially good, and a speaker who refused it would not be making a formal mistake; they would be revealing they do not know what west and east mean. Material inference is prior to formal-logical inference: logical vocabulary (if … then …, not, and) is, on the inferentialist view, an expressive resource that lets implicit material inferences be made explicit as further claims. This expressive view of logic is one of Brandom’s signature theses.

In this vault

Inferentialism

The semantic view, developed in its modern form by Robert Brandom (building on Sellars, Wittgenstein, and Quine), that the meaning of a sentence is its role in the inferential practices of a community of speakers — what asserting it entitles you to assert, what claims it is incompatible with, what would entitle you to assert it. Reference, truth, and representational content are downstream of inferential articulation rather than upstream of it. The slogan: meaning is use, formalised. The position is the philosophical underwriting of the Public Semantics / Commitment-based Semantics line in agent communication — a worked-out Semantics-Without-Minds that lets a wire-format trace carry full semantic content without invoking sender or receiver mental states.

In this vault

Articulating Reasons - Brandom — entry point (the 1998 Locke Lectures in book form)
Making It Explicit - Brandom — the full treatise
Empiricism and the Philosophy of Mind - Sellars — Sellars’s Myth of the Given is the historical hinge
Philosophical Investigations - Wittgenstein — Meaning As Use / language-games
Two Dogmas of Empiricism - Quine — Semantic Holism
Material Inference
Deontic Scorekeeping
Semantics-Without-Minds
Public Semantics
Mentalistic Semantics
Commitment-based Semantics
ACL Rethinking Principles — Singh’s social-agency programme is the ACL-side analogue
An Ontology for Commitments in Multiagent Systems - Singh
CBCL - Safe Self-Extending Agent Communication — engineering realisation at wire-format granularity

An Ontology for Commitments in Multiagent Systems - Singh

An Ontology for Commitments in Multiagent Systems: Toward a Unification of Normative Concepts

Reference: Singh, M. P. (1999). An Ontology for Commitments in Multiagent Systems: Toward a Unification of Normative Concepts. Artificial Intelligence and Law 7(1): 97–113. Kluwer. DOI · Author copy via Academia.edu · Singh publications (NCSU)

Summary

This paper is the formal core of Singh’s commitment-based programme — a piece that sits between the polemical Rethinking the Principles (1998) and the operationalised commitment machines line (Yolum & Singh 2002). Singh argues that the multiplicity of normative concepts used across MAS, deontic logic, and law — obligation, permission, prohibition, promise, contract, delegation, cancellation, release — can be unified by taking the social commitment as the basic ontological primitive and reconstructing the rest as patterns over commitments. A social commitment is a four-place relation: a debtor is committed to a creditor for the fulfilment of some condition in the context of a particular institution or social scope. Once these four roles are fixed, the standard normative operations — create, discharge, cancel, release, delegate, assign — become commitment-state transitions, and the deontic vocabulary becomes a derived layer over the commitment substrate.

The construction is deliberately public: commitments live in the social state, not in the heads of any agent. A commitment exists when a publicly observable act has created it (a promise speech act, a contract signing, an assertion under appropriate sincerity context); it persists until a publicly observable act has discharged or cancelled it. The truth-conditions for “agent A is committed” are externally checkable: they reference the social record, not A’s mental state. This is the exact alternative to the mentalistic semantics of FIPA / Cohen and Levesque 1995 that Rethinking the Principles called for. The paper also sets up the bridge to law: Singh notes the close fit with Jones and Sergot’s “count-as” relation, with deontic logic, and with the speaks-for tradition in distributed systems — establishing commitments as a unifying normative substrate across philosophy, law, MAS, and computer security.

For CBCL and the broader public-semantics line, this is the ontology document: it defines what “commitment” means precisely enough that protocol designers can map performatives onto commitment-state transitions and verifiers can monitor compliance from a transcript. The four-place structure (debtor, creditor, condition, context) maps almost directly onto the ledger-of-commitments architecture in Fornara & Colombetti 2004 and the dialect contracts in CBCL. The paper is also the place to cite when arguing that commitment-based ACL semantics is not merely a behavioural surrogate but a real normative theory with established connections to legal and deontic logic.

Key Ideas

Commitment as the primitive normative concept: a four-place relation C(debtor, creditor, condition, context) — agent x is committed to agent y for the fulfilment of condition q in the social context s. The four roles must always be specified; commitments without a creditor are degenerate.
Standard commitment operations: create (a new commitment comes into being via a public act), discharge (the condition is satisfied), cancel (the debtor unilaterally retracts, possibly incurring meta-commitment), release (the creditor waives), delegate (the debtor passes the obligation to a third party with creditor consent), assign (the creditor passes the entitlement).
Conditional commitments: CC(x, y, p ⊃ q, s) — x is committed to y to bring about q if p holds. The conditional structure handles contracts, contingent obligations, and protocol-state dependencies.
Discharge by satisfaction: a commitment is discharged when its condition is satisfied (in the relevant social interpretation); discharge is monotone — once discharged, the commitment is closed.
Deontic vocabulary as derived: obligation, permission, prohibition, right, and duty are reconstructable from commitment patterns plus the relevant institutional context.
Public, externally checkable semantics: commitments are facts about the social record, not about agent mental states. Verification is by inspection of the transcript and the institutional rules.
Bridges to legal informatics and deontic logic: the framework is explicitly compatible with Jones and Sergot’s count-as relation and with classical deontic-logic operators, positioning commitments as the unifier across philosophy, law, MAS, and distributed-security normative reasoning.

Connections

Conceptual Contribution

Claim: The proliferation of normative concepts across MAS, deontic logic, and law can be unified by taking the social commitment — a four-place relation C(debtor, creditor, condition, context) — as the basic primitive and reconstructing obligation, permission, prohibition, contract, and delegation as commitment patterns. Commitments are public: their existence is determined by observable acts and observable conditions, not by agent mental states.
Mechanism: Define commitments as four-place relations (debtor / creditor / condition / context) and conditional commitments analogously. Specify the operations create / discharge / cancel / release / delegate / assign as commitment-state transitions. Show how standard deontic-logic operators and standard legal concepts (promise, contract, breach, novation) reduce to patterns over these primitives. Sketch the bridge to Jones and Sergot’s count-as analysis of institutional facts.
Concepts introduced/used: Social Commitment, Conditional Commitment, Commitment Operations (create / discharge / cancel / release / delegate / assign), Debtor, Creditor, Condition, Context (Commitment), Deontic Reduction.
Stance: foundational technical paper / unifying ontology.
Relates to: The formal statement of the programme Singh 1998 argued for polemically; the bridge to the operational accounts in Yolum & Singh 2002, Yolum & Singh 2002b, and Fornara & Colombetti 2004. The philosophical complement is Brandom: Singh’s commitments are precisely the commitment leg of Brandom’s deontic scorekeeping triple. The legal complement is Jones & Sergot 1993 — count-as gives the institutional grounding for what makes a publicly observable act count as creating a commitment. The distributed-systems complement is the speaks-for tradition (Lampson et al. 1992) — credentials and delegated assertion authority are commitment patterns of the same family. CBCL’s dialect contracts and verdict ledger directly instantiate this ontology at wire-format granularity.

A Commitment-Based Approach to Agent Communication

Reference: Fornara, N. & Colombetti, M. (2004). Applied Artificial Intelligence 18(9–10): 853–867. DOI: 10.1080/08839510490509054. The journal article is paywalled; the open-access AAMAS-02 conference precursor — Operational Specification of a Commitment-Based Agent Communication Language (pp. 535–542) — captures the same model and is the locally archived source. Source file: fornara-colombetti-aamas02.pdf. URL

Summary

Fornara and Colombetti develop an object-oriented operational semantics for an Agent Communication Language grounded entirely in social commitments, intended for open environments populated by self-interested, heterogeneous agents who cannot be assumed to share an honest mental architecture. A Commitment is an abstract data type with fields Identifier, Debtor, Creditor, State ∈ {empty, cancelled, precommitment, conditional, active, fulfilled, violated}, Content (a temporal proposition), Condition (another temporal proposition), and Time-out. Its evolution is given by an explicit finite-state machine driven by two kinds of transitions: agent-invoked methods (mc, mp, ap, cc, cp, rp) and event-driven update rules triggered when the truth value of the content or condition resolves.

The authors’ key innovation over the Yolum-Singh treatment is the precommitment state, which models the social situation a directive speech act creates: the speaker cannot directly commit the hearer, so a request instantiates a precommitment whose debtor is the hearer; the hearer either accepts it (turning it into an active or conditional commitment), rejects it, fulfills it implicitly by performing the action, or lets the time-out elapse. This machinery yields uniform commitment-based definitions for Searle’s main illocutionary categories — assertives (inform, informIf, informRef), commissives (promise, conditionalPromise), and directives (request, conditionalRequest, accept, reject, yes/noQuestion, whQuestion) — and lets a propose act be defined compositionally as a conditional request conjoined with a conditional promise. A worked auction-style proposal protocol is given as an interaction diagram whose state contents are computed from the speech-act definitions, and whose soundness is checked by requiring that all final-state commitments be empty, fulfilled, or violated.

Key Ideas

Commitment-as-object: a commitment is an abstract data type with a state in {e, c, p, cc, a, f, v} whose dynamics are described by an explicit FSM.
Temporal proposition class: the content/condition of a commitment is a sentence + time interval + ∀/∃ mode + state, resolved by a domain “notifier” — separating what is committed from when and how its truth is observed.
Precommitment models directive speech acts: a request creates C(p, hearer, speaker, P|Q) that the hearer can accept (ap), reject (rp), implicitly fulfil (update rule 5), or let time out.
Conditional commitment with a temporal condition becomes active when the condition is satisfied and is automatically cancelled if the condition fails.
Five update rules link the truth-state of content and condition propositions to commitment-state transitions (active→fulfilled/violated, conditional→active/cancelled, precommitment→fulfilled).
Searle’s taxonomy of illocutionary acts is recovered by composition: inform, promise, request, accept/reject, yes/noQuestion, whQuestion, propose.
Soundness of an interaction protocol is checked by an interaction diagram in which every final state’s commitments are empty, fulfilled, or violated — a structural correctness criterion for negotiation protocols.
The notion of a conversational commitment (a meta-commitment to react to interlocutor speech acts) is sketched as the principled justification for the time-out field.

Connections

Conceptual Contribution

Claim: Speech-act semantics for an ACL should be specified operationally — as state-machine transitions over a public commitment data type — so that meaning is independent of any agent’s internal mental architecture, observable to third parties, and compositional across the speech-act taxonomy; in particular, the directive family requires a dedicated precommitment state because no agent can unilaterally commit another.
Mechanism: Define an abstract Commitment class with seven explicit states and a transition FSM driven by methods (mc/mp/ap/cc/cp/rp) plus five event-driven update rules that read truth-states of Temporal Proposition objects; define each Searle category by a single-line operation on commitment objects (inform := mc(a,b,P,T), request := mp(a,b,P,T), propose := conditionalRequest ∧ conditionalPromise, etc.); validate interaction protocols structurally via a state-content interaction diagram in which final-state commitments must all be empty/fulfilled/violated.
Concepts introduced/used: Commitment, Social Commitment, Precommitment, Conditional Commitment, Temporal Proposition, Commitment-Based Protocol, Commitment-based Semantics, Public Semantics, Verifiable Semantics, Speech Act Theory, Directives, Conversation Protocols, Interaction Protocols, Open Multi-Agent Systems, Conversational Commitment
Stance: formal-semantic / engineering
Relates to: Closest neighbour is Flexible Protocol Specification and Execution (Yolum & Singh, AAMAS-02) — the authors explicitly compare the two approaches: where Yolum-Singh use the Event Calculus and an abductive planner over create/discharge/cancel/release/assign/delegate, Fornara-Colombetti use an OO/FSM data type and add the precommitment apparatus to cover directives. Both belong to the social-semantics programme catalysed by ACL Rethinking Principles and formalised verifiability-style by Verifiable Semantics for ACLs; both are subsumed under the role-based unification of A Common Ontology Of ACLs. Repudiates the mentalistic line of FIPA-ACL / Intention Is Choice with Commitment for interoperable ACL semantics while keeping speech-act theory (Speech Acts - An Essay in the Philosophy of Language, A Taxonomy of Illocutionary Acts) as the organising taxonomy. The 2004 Applied AI version this entry primarily cites elaborates the AAMAS-02 model with extended treatment of negotiation protocols and the soundness-via-conversational-commitment programme that the authors’ later artificial-institutions work develops.

Tags

Agent Communication Languages

A concept hub for agent communication languages (ACLs): languages whose speech acts let software agents exchange beliefs, goals, and commitments.

Canonical Languages

KQML — original knowledge-query language
FIPA-ACL — standardised successor

Surveys & Principles

The State of the Art in Agent Communication Languages
Trends in Agent Communication Language
ACL Rethinking Principles — Singh, mental vs. social semantics
Agent Communication Languages - Rethinking the Principles
A Common Ontology Of ACLs
Toward Automated Evolution of ACLs
Towards Automating the Evolution of Linguistic Competence

Semantics

Conversations & Protocols

Domain instances

Common Business Communication Language — McCarthy 1975/1982
CBCL - Safe Self-Extending Agent Communication — O’Connor 2026 (LangSec ’26): contemporary Lean-verified DCFL-bounded ACL realising McCarthy’s CBCL vision

Assertion - Stalnaker

Assertion

Reference: Stalnaker, R. C. (1978). Assertion. In P. Cole (ed.), Syntax and Semantics 9: Pragmatics (pp. 315–332). New York: Academic Press. Reprinted in Stalnaker, Context and Content (Oxford UP 1999). PhilPapers record · SEP: pragmatics · SEP: presupposition

Summary

Stalnaker’s “Assertion” gives the canonical update-semantics account of what a speech act of asserting does, framed in terms of a common ground of mutually accepted propositions shared between conversational participants and a context set of possible worlds compatible with that common ground. To assert a proposition p is, prima facie, to propose that p be added to the common ground — equivalently, to propose that the context set be narrowed to its intersection with the set of worlds in which p is true. The hearer either accepts (the context set is updated) or challenges (the proposal stalls, the common ground is unchanged). The picture is symmetric, trace-checkable, and pragmatic: it tells you what an assertion does without taking a stand on the speaker’s inner mental state.

The paper develops three essential effects of assertion. (1) An assertion of p adds p to the common ground unless it is challenged. (2) The proposition asserted should be determinate — true or false at every world in the context set; if not, the context set must be re-coordinated first (anticipating the accommodation mechanism worked out in Lewis 1979). (3) The proposition asserted should partition the context set non-trivially: not be common-ground-true already, not be common-ground-false already, and not be context-incoherent. This third effect is the seed of Gricean informativeness as a built-in feature of the dynamics rather than a separately stated maxim. The framework anticipates the entire dynamic semantics tradition (Heim, Kamp, Veltman) and is the operational counterpart of Grice 1975: where Grice gives maxims governing rational conversation, Stalnaker gives the update mechanics conversation operates on.

For agent communication, Stalnaker is the philosopher who most directly anticipates trace-checkable assertion semantics. The common ground is a publicly observable object — what has been said and accepted — and assertion is a publicly observable update operation on it. There is no need to inspect any agent’s beliefs; the semantic content of an assertion is given by the update it proposes, and conformance with that semantics is checkable from a transcript. The natural pairing in this vault is with Singh 1998 on social-agency semantics, Fornara & Colombetti on commitment-based operational semantics, and ultimately CBCL — the common ground / context-set apparatus is precisely the kind of shared, monotone, trace-checkable object that monotone-verdict commitment protocols want.

Key Ideas

Common ground: the body of propositions mutually accepted (not necessarily believed) for purposes of conversation. The mathematical reflex is the context set — the set of worlds compatible with the common ground.
Assertion as context-set update: an assertion of p proposes narrowing the context set to the intersection with [[p]]. If accepted, the update goes through; if challenged, it stalls.
Three essential effects of assertion (the “essential effect” inventory): (i) the asserted proposition should be added to the common ground on acceptance; (ii) it must be determinate over the context set (true or false at each world); (iii) it must partition the context set non-trivially (informative).
Diagonalisation / two-dimensional accommodation: when an assertion’s content varies across worlds in the context set, the hearer can use the diagonal proposition — the function picking out, at each world, the content the assertion would have at that world — to recover a determinate update. This is the engine behind much of dynamic semantics’ treatment of indexicals and modals.
Pragmatic presupposition: a speaker presupposes q iff, in uttering an assertion, the speaker takes q to be in the common ground. Presupposition is a property of speakers in contexts, not of sentences in models — the move that allows accommodation to be modelled cleanly.
Context set is a public object: the framework is symmetric across participants — neither side has privileged access. Trace-checkability falls out.

Connections

Conceptual Contribution

Claim: Assertion is best modelled as a publicly observable update operation on the common ground of mutually accepted propositions. The semantic content of an assertion is determined by which possible worlds it eliminates from the context set, with no recourse to the speaker’s inner mental state required.
Mechanism: The common ground is the body of propositions the participants mutually accept for purposes of conversation; the context set is its set-theoretic reflex (worlds compatible with the common ground). An assertion of p proposes intersecting the context set with [[p]]. The three essential effects (informativeness, determinacy, acceptance-by-default) govern well-formed assertion; diagonalisation handles cases where content varies across the context set.
Concepts introduced/used: Common Ground, Context Set, Update Semantics, Diagonal Proposition, Pragmatic Presupposition, Accommodation, Essential Effect of Assertion.
Stance: foundational philosophical paper / canonical dynamic-pragmatic theory.
Relates to: Operational counterpart of Grice 1975 — where Grice supplies maxims of rational conversation, Stalnaker supplies the mechanics (context-set update) that conversation manipulates. Genealogically the foundation of the dynamic semantics tradition (Heim FCS, Kamp DRT, Veltman update semantics). For agent communication, the framework is the direct philosophical antecedent of public-semantics / commitment-based approaches: the common ground is a publicly observable, monotone, trace-checkable object — exactly the kind of state Singh’s social-agency semantics, Fornara & Colombetti’s operational commitment semantics, and CBCL’s ledger want. The deeper philosophical pair is Brandom: Stalnaker’s common-ground update is one of the two canonical formal models of deontic scorekeeping (the other being argumentation-style commitment stores after Hamblin).

Languages and Language - Lewis

Languages and Language

Reference: Lewis, D. K. (1975). Languages and Language. In K. Gunderson (ed.), Language, Mind, and Knowledge (Minnesota Studies in the Philosophy of Science, vol. 7, pp. 3–35). University of Minnesota Press. Reprinted in Philosophical Papers Volume I (Oxford UP 1983). URL (Minnesota Digital Conservancy)

Summary

“Languages and Language” is Lewis’s mature statement of the distinction between a language (an abstract function from sound-and-sign types to meanings, with no users) and language (a social phenomenon: a population’s practice of using a particular abstract language to communicate). The paper sharpens the framework introduced in Convention (1969) and rebuts an objection from Strawson and Searle that an account of language as convention — solving a coordination problem by mutual expectation — misses the normative heart of meaning. Lewis answers: it does not. A population uses an abstract language L iff there prevails in that population a convention of truthfulness and trust in L — a regularity by which speakers utter sentences of L only when they believe them true-in-L, and hearers respond by coming to believe the sentences uttered are true-in-L. The regularity is a convention in the technical Lewis 1969 sense: it solves a coordination problem (mutual intelligibility), it is sustained by mutual expectation (common knowledge that it is so sustained), and it has alternatives (some other abstract language could have played the same role).

The paper’s value over Convention is its precise account of the language–language relation. The abstract object L is a function from finite strings to truth-conditions (or, for non-declarative moods, to satisfaction-conditions). The social object — language — is the convention of truthfulness and trust in L. Different populations use different Ls; the same population can use several Ls for different domains. Meaning is not primarily a property of individual speakers’ minds: it is a property of the convention, fixed once we identify which L the population’s convention picks out. Speakers’ beliefs and intentions enter only via the convention-sustaining clauses (each speaker expects the others to be truthful-in-L and tries to be so themselves), not as the bearers of meaning.

For agent communication, “Languages and Language” is the cleanest philosophical statement of the public-semantics programme avant la lettre. The meaning of a wire-format performative is not the BDI state of the sender or receiver; it is the truth- or satisfaction-conditions assigned by the abstract language the protocol convention picks out. Two agents using FIPA-ACL are participating in a convention of truthfulness and trust in the abstract language defined by FIPA-ACL’s semantics. The convention requires only that agents act as if truthful-in-L; it does not require introspective access. This is exactly the dialect-and-protocol picture that Singh 1998 argues for, that commitment machines formalise, and that CBCL turns into a verified, self-extending wire format. Lewis 1975 is also the philosophical complement to Convention: where the 1969 book establishes the game-theoretic apparatus, the 1975 paper applies it to language and shows how to answer the standard objections from the speech-act tradition.

Key Ideas

Two senses of “language”: an abstract language L is a function from sentence-types to meanings (truth- and satisfaction-conditions); language (no article) is the social phenomenon — a population’s use of some L. Confusing the two is the source of much philosophy of language.
Convention of truthfulness and trust: a population uses L iff it has a convention (in the 1969 sense) of truthfulness in L (utter sentences only when believed true-in-L) and trust in L (hearers respond to such utterances by coming to believe the sentences true-in-L).
Meaning is a property of the convention, not the speaker: the convention picks out which L is in force; the meaning of a sentence in that population’s language is its meaning in L. Individual speaker mental states enter only as the conformity conditions of the convention.
Coordination problems and alternative languages: many abstract Ls could solve the population’s coordination problem; salience, precedent, and history pick one. Meaning is not arbitrary in function but contingent in particulars.
Reply to Strawson/Searle: the objection that convention-based accounts cannot capture the normative dimension of meaning is misplaced — the convention is itself a normative structure (it requires mutual expectation and conformity to be in force).
Multiple languages, one population: a population may use several Ls simultaneously — formal and informal registers, technical sub-languages, jargon — each sustained by its own convention.
Sentence moods and non-declaratives: imperatives and interrogatives are handled by extending the abstract L to assign satisfaction- and answerhood-conditions; the convention-of-truthfulness-and-trust generalises to a convention of acting as if the satisfaction-conditions held.

Connections

Conceptual Contribution

Claim: Sharpen the Convention 1969 picture into a precise account of how an abstract language L (a function from sentences to truth-/satisfaction-conditions) gets in force in a population: by a convention of truthfulness and trust in L. Meaning is a property of the convention, not of individual speakers’ mental states.
Mechanism: Define abstract languages as functions from sentence-types to truth- and satisfaction-conditions. Define use of L by population P as the prevalence in P of a convention (in the Lewis 1969 sense) of being truthful in L and trusting in L. Show how this answers Strawson’s and Searle’s normativity objection (the convention is itself normative) and how it generalises to non-declarative moods (satisfaction-conditions) and to populations using multiple Ls.
Concepts introduced/used: Abstract Language, Convention of Truthfulness, Convention of Trust, Truthfulness and Trust, Sentence Mood, Pragmatic Presupposition, Public Semantics.
Stance: foundational philosophical paper.
Relates to: Direct sequel to Lewis 1969 (Convention) — the 1969 book gives the game-theoretic foundations, the 1975 paper applies them to language. Operational complement to Stalnaker 1978: where Stalnaker gives the update mechanics of assertion, Lewis 1975 says what makes a particular abstract language the one the participants are updating in. For agent communication, this is the cleanest philosophical statement of the public-semantics programme: the meaning of an ACL performative is fixed by the protocol convention’s chosen L, not by speakers’ BDI states — exactly the picture Singh 1998 argues for, commitment machines formalise, and CBCL turns into a verified wire format. The view also locates Wittgensteinian meaning-as-use within an explicit game-theoretic setting (Lewis’s convention is the formal regulariser of Wittgenstein’s language-games), and is compatible with Brandomian inferentialism as a downstream layer (inferential articulation is what gives L its truth-conditions in the first place).

Convention - Lewis

Convention: A Philosophical Study

Reference: Lewis, D. K. (1969). Convention: A Philosophical Study. Harvard University Press, Cambridge MA. (Reprinted 2002, Blackwell.) SEP entry on Convention · Wiley publisher page (book; no full-text OA.)

Summary

Lewis offers the first rigorous game-theoretic analysis of how shared conventions — including, paradigmatically, the conventions of language — arise and sustain themselves among rational agents without explicit agreement. The book opens by defining a coordination problem: a situation in which several agents have multiple equilibria available, all parties prefer reaching some equilibrium to none, and they are largely indifferent (or have non-conflicting preferences) over which equilibrium they reach. Lewis’s central thesis is that a convention is a regularity in behaviour that is one solution to a coordination problem, sustained by mutual expectation — each party expects the others to follow the regularity, expects the others to expect them to follow it, and so on up an infinite hierarchy that Lewis was the first to formalise as common knowledge. The book applies this analysis to driving conventions (drive on the right vs left), signalling, currency, and at length to language: the conventions of meaning are coordination equilibria sustained by mutual expectation in a population of speakers; semantic content is what would be the case if the convention were followed. Lewis’s framework supplies the philosophical foundation for every later treatment of emergent and negotiated meaning — emergent-communication research in MAS and deep learning, the ACL evolution programme, and the language-games tradition (Wittgenstein operationally, Steels formally) all proceed in the conceptual space Lewis defined. The common-knowledge construction is independently a foundational result for distributed-systems theory (Halpern & Moses 1990) and game theory (Aumann 1976).

Key Ideas

Coordination problem: a strategic situation with multiple Pareto-comparable equilibria where no party prefers a non-equilibrium outcome and the parties’ preferences over equilibria largely coincide. The classical examples — driving side, meeting place — generalise to language, money, social roles.
Convention as a self-sustaining regularity: a regularity R is a convention iff (i) almost everyone conforms to R, (ii) almost everyone expects almost everyone else to conform to R, (iii) almost everyone prefers conforming on the assumption that others conform, and (iv) some alternative regularity could have been the convention instead (no party of the convention is intrinsically preferred).
Common knowledge: the infinite hierarchy of mutual expectation that sustains a convention — A knows that B follows R; A knows that B knows that A follows R; and so on. Lewis was the first to give a formal account of this in social terms; the construction was rediscovered by Aumann in game theory and Halpern–Moses in distributed systems.
Salience and precedent as convention selectors: when multiple equilibria are available, salient features (Schelling’s focal points, see The Strategy of Conflict) and historical precedent select among them. There is no rationality-driven argument for which equilibrium becomes conventional; the answer is contingent on saliency.
Language as convention: meaning is what would obtain if the convention were followed. Truth-conditions, communicative force, and reference are all conventionally fixed — but the convention is not arbitrary, it is sustained by everyone’s expectation that everyone else will use words a particular way.
Conventions vs explicit agreements: Lewis argues that explicit agreement is neither necessary nor sufficient for convention — many conventions arise without agreement (precedent does the work) and many agreements never become conventions (because mutual expectation does not develop).
Population vs pair: conventions are population-level facts; one cannot have a convention with a single partner. Mutual expectation must extend across the relevant community for the regularity to be convention-grade.

Connections

Conceptual Contribution

Claim: Conventions — including the conventions of language — are best analysed as solutions to coordination problems sustained by mutual expectation (formally, common knowledge) in a population of rational agents. There is nothing arbitrary about the convention’s function, but the particular regularity that becomes conventional is contingent on salience, precedent, and historical accident.
Mechanism: Game-theoretic analysis of coordination problems with multiple equilibria; definition of convention via four clauses (conformity, mutual expectation, conditional preference, alternativeness); explicit construction of common knowledge as an infinite hierarchy of expectations; application to driving conventions, signalling, currency, and at length to language semantics.
Concepts introduced/used: Coordination Game, Convention (Lewis), Common Knowledge (Convention), Mutual Expectation, Focal Point (via dialogue with Schelling), Salience, Precedent, Convention vs Agreement.
Stance: foundational philosophical monograph.
Relates to: Direct philosophical foundation for every later treatment of emergent meaning and negotiated language: Steels’ language games are operational realisations of Lewis’s coordination-problem analysis with explicit interaction protocols; Lazaridou et al. and the deep-learning emergent-communication line train neural agents to converge on Lewis-style conventions in referential games. The ACL-evolution programme (Toward Automated Evolution of ACLs, Towards Automating the Evolution of Linguistic Competence) treats the ACL itself as an evolving Lewis-convention. Lewis’s common-knowledge construction is independently the foundation of Halpern & Moses 1990 in distributed systems and Aumann (1976) in game theory — distributed protocols and conventional language share the same mathematical object. The framework also clarifies what is at stake in the Mentalistic Semantics vs Public Semantics debate in ACLs: Lewis-style conventions are public-semantics objects (mutual-expectation regularities) but their stability depends on something close to mentalistic conditions (each agent’s expectations about others’ beliefs), so the two semantic families are dual aspects of the same phenomenon rather than competitors. Why AI Agents Communicate In Human Language revisits Lewis from the LLM-agent angle: natural language is a particular Lewis-convention (a contingent equilibrium) and not necessarily the optimal one for inter-agent coordination.

Tags

#convention #coordination #common-knowledge #lewis #philosophy-of-language #foundations #emergent-meaning

Logic and Conversation

Reference: Grice, H. P. (1975). In P. Cole & J. L. Morgan (Eds.), Syntax and Semantics, Vol. 3: Speech Acts, pp. 41–58. Academic Press. (Originally delivered as the 1967 William James Lectures at Harvard.) Source file: grice_logic_and_conversation.pdf. URL

Summary

Grice’s foundational paper introduces the theory of conversational implicature: the mechanism by which speakers convey more than they literally say. Starting from the divergences formalists find between natural-language connectives (and, or, if, not, all, some) and their formal analogues, Grice argues the divergences do not show natural language is defective; rather, they arise from principles governing rational cooperative exchange, not from logical form.

At the centre is the Cooperative Principle: “Make your conversational contribution such as is required, at the stage at which it occurs, by the accepted purpose or direction of the talk exchange in which you are engaged.” The principle decomposes into four categories of maxims — Quantity (be as informative as required, no more), Quality (try to make your contribution true), Relation (be relevant), and Manner (be perspicuous). Speakers exploit these maxims — by apparently flouting them while the Cooperative Principle remains in force — to generate conversational implicatures that the hearer can calculate. The paper distinguishes what is said from what is implicated, and conventional from conversational implicatures, establishing the framework in which pragmatics has operated ever since. Its picture of communication as rational, cooperative, defeasible inference over an idealised shared purpose became a touchstone for ACL design, HCI dialogue systems, and the pragmatics of LLM prompting.

Key Ideas

What is said vs. what is implicated.
Conventional vs. conversational implicature.
Cooperative Principle as constitutive of rational discourse.
Four maxim categories: Quantity, Quality, Relation, Manner.
Implicatures arise from (apparent) maxim-flouting under the CP.
Implicatures are calculable, cancellable, non-detachable.
Natural-language/formal-logic divergences need not reflect semantic defect.

Connections

Conceptual Contribution

Claim: Successful communication rests on a presumed Cooperative Principle and its four categories of maxims; apparent violations of the maxims, against the background of presumed cooperation, generate implicatures — inferences about speaker meaning that go beyond literal content.
Mechanism: Grice frames discourse as goal-directed rational cooperation; derives the Cooperative Principle as a rationality constraint on contributions; distinguishes its maxims by Kantian category; shows that a speaker who says p while flouting a maxim (e.g., irrelevantly, uninformatively, or obscurely) signals that a further proposition q must be inferred to restore the presumption of cooperation — q is then conversationally implicated. Implicatures are calculable from the maxims plus context, cancellable without contradiction, and non-detachable from what is said.
Concepts introduced/used: Cooperative Principle, Conversational Implicature, Conventional Implicature, Gricean Maxims, Speaker Meaning, What Is Said
Stance: philosophical/pragmatic theory
Relates to: Complements the illocutionary classification of A Taxonomy of Illocutionary Acts by supplying a theory of pragmatic enrichment; informs the semantic/pragmatic layer distinctions in Agent Communication Languages and critiques of mentalistic ACL semantics in Agent Communication Languages - Rethinking the Principles; underpins the rational-speaker assumptions implicit in prompt engineering and LLM Agents.

Tags

Speech Acts - An Essay in the Philosophy of Language

Speech Acts: An Essay in the Philosophy of Language

Reference: John R. Searle (1969). Speech Acts: An Essay in the Philosophy of Language. Cambridge University Press. Source file: Searle 1969 - Speech Acts.pdf. URL

Summary

Searle’s foundational monograph gives speech-act theory its first systematic, philosophically defended treatment. Extending Austin’s How to Do Things with Words, it argues that the minimal unit of linguistic communication is neither the symbol nor the sentence but the production of the symbol in the performance of a speech act. Searle develops a constitutive-rule analysis of illocutionary acts, codifies the felicity conditions of paradigm acts (promising, referring, predicating, asserting), and uses the framework to attack the fact/value distinction, deriving “ought” from “is” via the institutional fact of promising.

The book introduces the now-canonical machinery that McCarthy’s Elephant 2000 - A Programming Language Based on Speech Acts imports as programming-language primitives: the force/content distinction F(p), propositional-content conditions, preparatory conditions, sincerity conditions, and essential conditions. It is also the direct ancestor of Foundations Of Illocutionary Logic, which formalises what Searle here develops discursively.

Key Ideas

Speech acts as the unit of meaning: producing a sentence under appropriate conditions is performing an illocutionary act; meaning reduces to a recursive theory of these acts.
Force vs. content F(p): every utterance factors into illocutionary force (assert, promise, request, …) and propositional content.
Constitutive rules: rules of the form “X counts as Y in context C” create institutional facts (promises, marriages) rather than merely regulating antecedent behaviour.
Felicity conditions for promising (canonical analysis): propositional-content, preparatory, sincerity, and essential conditions — the template every later ACL performative inherits.
Reference and predication as distinct speech acts, each with their own rules.
Institutional facts and the is/ought derivation via promising as a constitutive practice.

Connections

Elephant 2000 - A Programming Language Based on Speech Acts — McCarthy’s direct source for the speech-act vocabulary of Elephant
Foundations Of Illocutionary Logic — Searle & Vanderveken 1985, formalises the present book
Speech Act Theory
Speech Acts
Performatives
Illocutionary Force
Sincerity Conditions
Preparatory Conditions
Agent Communication And Institutional Reality
KQML
FIPA-ACL
Agent Communication Languages
Commitment-based Semantics

Conceptual Contribution

Claim: Linguistic communication is irreducibly act-theoretic: the minimal unit of meaning is the illocutionary act, analysable by constitutive rules and felicity conditions, and this analysis extends to reference, predication, and the generation of institutional facts.
Mechanism: Case studies of promising, referring, and asserting yield a recursive schema F(p) with four condition-types (propositional-content / preparatory / sincerity / essential). The schema is then redeployed to distinguish regulative from constitutive rules and to dissolve the classical is/ought problem by showing that uttering “I promise” institutionally constitutes an obligation.
Concepts introduced/used: Performatives, Illocutionary Force, Sincerity Conditions, Preparatory Conditions, Speech Act Theory, Institutional Reality, Commitment-based Semantics
Stance: foundational / philosophical
Relates to: Imported wholesale by Elephant 2000 - A Programming Language Based on Speech Acts as the philosophical basis for speech-act I/O; formalised by Foundations Of Illocutionary Logic; re-examined for multi-agent systems in Agent Communication And Institutional Reality and operationalised in KQML / FIPA-ACL performative sets. McCarthy explicitly departs from Searle by adopting a design stance on these primitives — see Abstract Performative.

Tags

How to Do Things with Words

Reference: Austin, J. L. (1962). How to Do Things with Words. The William James Lectures delivered at Harvard University in 1955. Oxford: Clarendon Press (ed. J. O. Urmson). Source file: austin-1962-how-to-do-things-with-words.pdf. Cited by Elephant 2000 - A Programming Language Based on Speech Acts (McCarthy 1989).

Summary

Austin’s posthumously edited William James Lectures are the founding text of speech-act theory. Austin begins by isolating a class of utterances - “performatives” (e.g. “I promise”, “I do”, “I name this ship”) - that do not describe or report but instead perform an action, and cannot be evaluated as true or false but only as happy or unhappy (felicitous or infelicitous). Through twelve lectures he progressively dissolves the performative/constative distinction in favour of a general theory in which every utterance performs a locutionary, illocutionary, and perlocutionary act. The taxonomy of illocutionary force (verdictives, exercitives, commissives, behabitives, expositives) directly anticipates Searle/Vanderveken’s Foundations Of Illocutionary Logic and the performative vocabulary of KQML and FIPA-ACL.

Key Ideas

Performative utterance: saying is doing. “I promise” is not a report of a promise - it is the promise.
Felicity conditions: instead of truth conditions, performatives succeed or fail by satisfying procedural, sincerity, and uptake conditions.
Locution / illocution / perlocution: three layers of every speech act - what is said, what is done in saying it, and what is achieved by saying it.
Five illocutionary classes (verdictives, exercitives, commissives, behabitives, expositives) - taxonomy later refined by Searle into five primitives.
Dissolution of the performative/constative boundary: assertion itself turns out to be a species of illocutionary act.

Connections

Conceptual Contribution

Claim: Many utterances are not descriptions that can be true or false but actions that are performed in the saying; and on closer inspection the descriptive/performative divide collapses, so every utterance is a layered act with illocutionary force.
Mechanism: Contrast between constative and performative utterances; introduction of felicity conditions (A.1-A.2, B.1-B.2, Gamma.1-Gamma.2 misfires and abuses); the tri-layer locution/illocution/perlocution analysis; provisional five-way classification of illocutionary verbs.
Concepts introduced/used: Performatives, Illocutionary Force, Felicity Conditions, Locutionary Act, Perlocutionary Act, Speech Act Theory
Stance: foundational / ordinary-language-philosophy
Relates to: Provides the raw speech-act ontology that Searle formalises in Speech Acts and that McCarthy imports in Elephant 2000 - A Programming Language Based on Speech Acts; the felicity-condition apparatus recurs under “feasibility” and “sincerity” preconditions in FIPA-ACL semantics and in Commitment-based Semantics.

Tags

#speech-acts #philosophy-of-language #foundational #austin #performatives

Speech Act Theory

Philosophy-of-language framework (Austin, Searle, Vanderveken) in which utterances perform actions (illocutionary acts) — the semantic backbone of most Agent Communication Languages.

Sources

Foundations Of Illocutionary Logic — Searle & Vanderveken
Three Models for the Description of Language — Chomsky, foundations
Agent Communication And Institutional Reality

Applied in

Lineage

graph TD
  A["Austin (1962)<br/>How to Do Things with Words"] --> A1[Locutionary]
  A --> A2[Illocutionary]
  A --> A3[Perlocutionary]
  A2 --> S["Searle (1969, 1975)<br/>Speech Acts · Taxonomy of Illocutionary Acts"]
  S --> S1[Assertives]
  S --> S2[Directives]
  S --> S3[Commissives]
  S --> S4[Expressives]
  S --> S5[Declarations]
  G["Grice (1975)<br/>Logic and Conversation"] -.cooperative principle.-> S
  S --> V["Searle & Vanderveken (1985)<br/>Foundations of Illocutionary Logic"]
  V --> M["McCarthy (1989)<br/>Elephant 2000"]
  V --> KQML[KQML performatives]
  V --> FIPA[FIPA-ACL performatives]
  M --> FIPA
  KQML --> ACL[[Agent Communication Languages]]
  FIPA --> ACL

Papers: How to Do Things with Words · Speech Acts - An Essay in the Philosophy of Language · A Taxonomy of Illocutionary Acts · Logic and Conversation · Foundations Of Illocutionary Logic · Elephant 2000 - A Programming Language Based on Speech Acts

Mentalistic Semantics

ACL semantics in which each message commits the sender’s (and sometimes receiver’s) beliefs and intentions — powerful but unverifiable from outside.

In this vault

Pragmatist Semantics

Family of approaches that ground meaning in use — communicative practices, normative attitudes, commitments and entitlements — rather than in mind-independent reference. Brandom’s Making It Explicit is the canonical contemporary statement.

In this vault

Making It Explicit - Brandom

Making It Explicit: Reasoning, Representing, and Discursive Commitment

Reference: Brandom, R. B. (1994). Making It Explicit: Reasoning, Representing, and Discursive Commitment. Harvard University Press, Cambridge MA. ~700 pp. URL (Part One PDF, author-hosted) · Internet Archive · SEP: inferentialism

Summary

Making It Explicit is Brandom’s full statement of the inferentialist programme — the long, technical book that Articulating Reasons (2000) compresses into six lectures. Where the shorter book is the entry point, MIE is the reference manual: it works out, at the level of detail required to settle objections, how the basic discursive practice of giving and asking for reasons can serve as the foundation for an entire theory of meaning — including the parts (reference, truth, objectivity, intentionality) that representationalism takes as primitive. The book unfolds in two large parts: a pragmatic part, in which Brandom develops the deontic scorekeeping model of assertion and shows how it can recover everything one wants from a notion of speech act without recourse to mental states, and a semantic part, in which the recovery of singular terms, predicates, propositional content, and ultimately the de re / de dicto distinction is carried out in scorekeeping terms.

The book’s intellectual ancestry is openly stated: Quine on semantic holism and the analytic–synthetic collapse, Sellars on the Myth of the Given and the space of reasons, and Wittgenstein on meaning as use and language-games, all metabolised through a Hegelian appreciation of the social character of normativity. The technical innovation is to take Sellars’s insight — that the difference between a parrot trained to say “that’s red” and a person saying it is not phenomenological but inferential (a person can deploy the claim in the game of reasons) — and turn it into a full-scale semantic theory. The result is the most developed semantics-without-minds in the analytic tradition: a worked-out alternative to the mentalistic picture that has dominated philosophy of language since Searle and the early Cohen–Levesque tradition in ACL design.

For the agent-communication line, MIE is the place to send sceptics. The standard worry about public-semantics / commitment-based ACL design is that it gives up on “real” meaning in exchange for trace-checkability. Brandom’s answer, in a thousand pages, is no: deontic scorekeeping is not a thin behavioural surrogate for a richer mentalistic semantics — it is the foundation from which mentalistic talk is derivable. If Brandom is right, then Singh 1998’s move from BDI semantics to social-commitment semantics is not a retreat under pressure of verifiability; it is the correct place to ground meaning, with verifiability as a downstream bonus.

Key Ideas

Deontic scorekeeping as the basic discursive practice: speakers track, for themselves and each other, commitments (claims undertaken), entitlements (claims one is licensed to undertake), and incompatibilities (pairs of commitments that cannot both be entitled). Assertion is the basic move; the score is the running ledger.
Material inference as ground floor: inferences whose goodness is part of the meaning of the constituent terms (Pittsburgh is west of Princeton ⇒ Princeton is east of Pittsburgh) are prior to formal logical inference. Logic is a downstream expressive resource.
The expressive role of logic: conditionals, negation, and other logical vocabulary serve the function of making implicit inferential commitments explicit as new claims. This is the expressive (not foundational) role of logic.
De re / de dicto and singular terms: even classically representationalist topics — quantifying in, anaphora, singular reference — are reconstructed in scorekeeping terms, without taking reference as primitive.
Sapience without sentience: the distinction between concept-mongering creatures and the rest of nature lies in participation in the game of giving and asking for reasons, not in phenomenology.
Normative pragmatism: the social practice of holding one another accountable for commitments is the unanalysed foundation. Norms are instituted by the practice of scorekeeping, not read off antecedent facts.
Anti-representationalist but not anti-realist: truth, objectivity, and a mind-independent world are recovered from the perspectival structure of scorekeeping — not given up.

Connections

Conceptual Contribution

Claim: Linguistic meaning, including reference and objectivity, can be fully reconstructed from the social practice of deontic scorekeeping — undertaking, attributing, and tracking commitments and entitlements — without taking any mental state or representational primitive as basic.
Mechanism: A two-part construction. Pragmatic part: the basic act of asserting is the undertaking of a commitment; scorekeeping practices track commitments, entitlements, and incompatibilities. Semantic part: propositional content is the inferential role of a sentence in the scorekeeping practice; singular terms, predicates, de re / de dicto, and reference are recovered from the structure of perspectival scorekeeping. Logic is an expressive resource that makes implicit inferential commitments explicit.
Concepts introduced/used: Inferentialism, Deontic Scorekeeping, Material Inference, Commitment (Brandom), Entitlement (Brandom), Incompatibility (Brandom), Expressive Role of Logic, Sapience vs Sentience, De Re vs De Dicto, Normative Pragmatism, Semantics-Without-Minds.
Stance: foundational philosophical treatise.
Relates to: The book-length statement of which Articulating Reasons is the readable extract; read MIE only when the lectures leave a question unresolved. Genealogically continues the Wittgenstein / Sellars / Quine line — Sellars’s Myth of the Given is the antecedent move; Brandom’s scorekeeping is its destination. For agent communication, MIE is the deep philosophical underwriting of the public-semantics / commitment-based programme — Singh, Fornara & Colombetti, Yolum & Singh, and ultimately CBCL can all be read as engineering instantiations of fragments of the MIE picture.

Belief-Desire-Intention

Alternative spelling of the BDI agent architecture; see BDI for the canonical entry.