Feasibility Precondition

In the FIPA-ACL / Cohen–Levesque semantics of communicative acts, the condition that must hold for an agent to sincerely perform a speech act — paired with the rational effect, the result the agent intends to bring about. For an inform, the feasibility precondition requires (roughly) that the sender believes the proposition and believes the receiver does not already hold a view on it. The FP/RE pair is the core of Mentalistic Semantics.

In this vault

Backlinks

Linked Pages

Communicative Actions for Artificial Agents - Cohen Levesque

Communicative Actions for Artificial Agents

Reference: Cohen, P. R. & Levesque, H. J. (1995). Communicative Actions for Artificial Agents. In Proceedings of the First International Conference on Multi-Agent Systems (ICMAS-95), San Francisco, June 1995, pp. 65–72. AAAI Press. Reprinted in J. M. Bradshaw (ed.), Software Agents (AAAI Press / MIT Press 1997), ch. 19. URL (AAAI PDF)

Summary

This paper is the high-water mark of mentalistic ACL semantics: the most explicit, systematic statement of the position that an agent communication act is a complex operator on the BDI states of sender and receiver, and that the semantics of an ACL performative is given by feasibility preconditions and rational effects expressed in modal logic over those mental states. Cohen and Levesque extend the Cohen–Levesque 1990 modal logic of intention into a logic of rational action in which speech acts are first-class actions whose definitions are derivable from more basic actions of attempting to bring about a state of affairs, together with assumed Gricean rationality on the part of both agents. The standard FIPA-ACL semantics in the FIPA Communicative Act Library Specification (FIPA00037) is essentially a streamlined adaptation of the Cohen–Levesque framework.

The mechanism is precise. A speech act e performed by speaker s toward hearer h has a feasibility precondition (e.g. s believes p, s believes h does not know p, s intends h to come to know p) and a rational effect (e.g. h believes p because h believes s sincerely informed). The semantics of inform, request, promise, commit, propose, and other performatives are derived by composition from the more primitive attempt: a request is an attempt to bring about that the hearer perform an action and that the hearer believe the speaker wants the action performed; an inform is an attempt to bring about that the hearer come to believe p and to know the speaker believes p; and so on. The framework is mathematically beautiful and ontologically heavy: it requires every speech act to be defined in terms of nested beliefs and intentions of speaker and hearer, often to several levels of nesting.

This is precisely why Singh 1998 writes the Rethinking critique. The Cohen–Levesque definitions are unverifiable in practice: no external observer can check that an agent believed p when it sent inform(p); the inferential web that fixes whether the agent “really” performed an inform speaks entirely about the agent’s mental state, which is exactly the inscrutable thing the protocol participants do not have access to. The paper is therefore the canonical negative example for CBCL and the commitment-based tradition: it shows what a fully worked-out mentalistic semantics looks like, and that shows why the field has had to move on. The right way to read it in 2026 is as the high statement of a coherent but unverifiable position, not as a blueprint to implement.

Key Ideas

Speech act = action on mental states: a communicative act is a complex action whose semantics is given by feasibility preconditions and rational effects expressed over the BDI states of speaker and hearer.
Attempt as the primitive: more elementary than the standard speech-act categories is the action of attempting — an agent attempts an action toward an end if and only if it performs the action with that goal and the belief that the action is the means.
Composition of performatives: standard performatives (inform, request, promise, propose, confirm, agree, refuse) are derived by composing attempt with specific mental-state preconditions and goals.
Sincerity and competence as background assumptions: the rational effects only follow if speaker and hearer are sincere (no lying) and competent (no false beliefs). When these fail, the framework’s predictions silently fail too.
Joint intentions in conversation: extends the 1990 framework with joint intentions — for conversational acts like agreement, both parties acquire a shared intention with mutual belief.
Verifiability is a known cost: the paper acknowledges that the mental-state preconditions are not externally observable; it argues this is the price of a real semantics rather than a behavioural surrogate.
Closest formal ancestor of FIPA: the FIPA-ACL CAL spec (FIPA00037) is a direct adaptation of this framework with light editorial smoothing.

Connections

Conceptual Contribution

Claim: Communicative acts can be given precise semantics by defining them as complex actions on the BDI states of sender and receiver, derived by composition from the primitive notion of attempt under shared rationality assumptions. The semantics of an ACL performative is its feasibility precondition and rational effect, expressed in modal logic over beliefs, goals, and intentions.
Mechanism: Extend the Cohen–Levesque 1990 modal logic of intention with a notion of attempt (an agent attempts an action toward an end iff it performs the action with that goal and the belief that the action serves the goal). Define each standard performative by composition: inform(s,h,p) requires s believes p, s believes h does not know p, s intends h to come to know p; the rational effect is that h comes to believe p by mutual recognition of s’s sincerity. Similar definitions for request, promise, propose, agree, refuse, with joint-intention machinery handling conversational acts.
Concepts introduced/used: Attempt (Cohen-Levesque), Feasibility Precondition, Rational Effect, Mentalistic Semantics, Joint Intentions, Sincerity Condition, Communicative Act Library.
Stance: foundational technical paper / formal-semantics manifesto.
Relates to: The closest formal ancestor of the FIPA Communicative Act Library (FIPA00037) — the FIPA spec is essentially a streamlined adaptation of this framework. It is the negative example against which the public-semantics / commitment-based line defines itself: Singh 1998 argues precisely that the BDI preconditions are unverifiable and that ACL semantics should be grounded in observable social commitments instead. Yolum & Singh 2002, Fornara & Colombetti 2004, and Singh 1999 develop the public alternative. CBCL then operationalises that alternative as a verified, trace-checkable, self-extending wire format — explicitly not what Cohen and Levesque built. The philosophical critique of mentalistic semantics runs deeper, through Sellars / Brandom / <em>MIE</em> — Cohen–Levesque takes mental states as pre-given semantic primitives, which is the move inferentialism rejects.

FIPA-ACL Specifications

Reference: Foundation for Intelligent Physical Agents (2002). FIPA ACL Message Structure Specification (FIPA00061) and FIPA Communicative Act Library Specification (FIPA00037). Geneva, December 2002. (FIPA was absorbed into the IEEE Computer Society in 2005; specifications remain the canonical reference.) FIPA00061 (Message Structure) · FIPA00037 (Communicative Act Library) · FIPA00067 (Agent Message Transport) · IEEE FIPA standards committee

Summary

The FIPA-ACL specifications are the standards-track distillation of the late-1990s mentalistic ACL programme: the wire format and semantics that “ended up shipping” as the canonical example of an industry-grade agent communication language. The suite splits into three documents that matter for ACL design. FIPA00061 specifies the message structure — the surface syntax of an ACL message as a parameterised performative envelope with :sender, :receiver, :content, :language, :ontology, :protocol, :conversation-id, :reply-with, :in-reply-to, :reply-by, and a small set of related parameters. FIPA00037 specifies the communicative act library — twenty-two performatives (accept-proposal, agree, cancel, cfp, confirm, disconfirm, failure, inform, inform-if, inform-ref, not-understood, propagate, propose, proxy, query-if, query-ref, refuse, reject-proposal, request, request-when, request-whenever, subscribe) — each given by feasibility precondition (FP) and rational effect (RE) expressed in the FIPA Semantic Language (SL) over beliefs, intentions, and uncertainty. FIPA00067 specifies the message transport (HTTP, IIOP, WAP carriers; envelope and routing).

Two features make FIPA-ACL the canonical reference point — and the canonical negative example — for ACL semantics work. First, the direct lineage from Cohen and Levesque: the FP/RE structure of FIPA00037 is a streamlined adaptation of Cohen and Levesque 1995. The semantics of inform(p) is, modulo notation, exactly the Cohen–Levesque definition: the sender believes p, believes the receiver does not know p, and intends the receiver to come to believe p. The semantics of request mirrors attempt over a hearer action. Second, the unverifiability problem: precisely because the semantics is given in terms of sender and receiver mental states, no external observer can determine whether a message is FIPA-conformant. A platform that ships inform(p) in violation of its feasibility preconditions (e.g. the sender does not believe p, i.e. is lying) is indistinguishable on the wire from a platform that ships a conformant inform. This is the deficiency Singh 1998 names, Wooldridge formalises, and the commitment-based semantics tradition fixes.

For this vault, FIPA-ACL is the engineered artefact against which the public-semantics critique runs. The spec is well-engineered as a message format — the envelope, the protocol-id mechanism, the ontology / language slots are all sound — and the wire format itself has aged well. What has not aged well is the semantics by mental-state precondition: it is unverifiable, hostile to heterogeneous deployment, and incompatible with the public-semantics / commitment-based programme that CBCL inherits. The right reading is: keep the engineering, replace the semantics.

Key Ideas

Three-part suite: FIPA00061 (message structure), FIPA00037 (communicative act library), FIPA00067 (message transport).
Message structure: :sender, :receiver, :content, :language, :ontology, :protocol, :conversation-id, :reply-with, :in-reply-to, :reply-by, :performative. Standard envelope; the :content slot carries an arbitrary content-language expression interpreted by the :ontology.
Twenty-two performatives: from accept-proposal through subscribe, organised loosely into Searlean families (assertives, directives, commissives, declaratives). The set is small enough to remember and rich enough to cover most multi-agent interaction patterns.
Semantic Language (SL): FIPA’s formal language for FP/RE definitions; a modal logic over belief, uncertainty, intention, and action, descended from Cohen and Levesque.
Feasibility precondition / rational effect: each performative is defined by an FP (what must hold for the agent to perform the act in good faith) and an RE (what the agent intends to bring about). Both involve nested beliefs and intentions of sender and receiver.
Interaction protocols: FIPA also standardises a small set of interaction protocols (FIPA-Request, FIPA-Query, FIPA-ContractNet, FIPA-IteratedContractNet, FIPA-EnglishAuction, FIPA-DutchAuction, FIPA-Brokering, FIPA-Recruiting, FIPA-Subscribe, FIPA-Propose) — finite state machines over performatives that script common conversational patterns.
Unverifiability is intrinsic: the FP/RE conditions are stated over mental states; no external observer can check conformance without inspecting agent internals — a known design cost and the central target of the social-agency critique.

Connections

Conceptual Contribution

Claim: A standardised ACL can be built from a small set of performatives, each given by mental-state preconditions and intended effects in a modal logic, embedded in a standardised message envelope, with a standard library of interaction protocols. The result is the canonical industry ACL.
Mechanism: Three coordinated specs. FIPA00061 fixes the wire format (envelope parameters and message routing). FIPA00037 fixes the performative semantics in SL, with each of twenty-two performatives given by FP and RE in terms of belief, uncertainty, and intention nested over sender and receiver. FIPA00067 specifies the message transport. A small library of interaction protocols (FIPA-Request, FIPA-ContractNet, etc.) gives canonical conversational patterns as finite state machines over performatives.
Concepts introduced/used: FIPA Performative, Semantic Language (FIPA SL), Feasibility Precondition, Rational Effect, FIPA Interaction Protocol, ContractNet, ACL Message Envelope, Conversation ID.
Stance: standards specification suite / industry deliverable.
Relates to: Direct standardisation of Cohen and Levesque 1995 — the FIPA00037 semantics is essentially that paper’s framework with editorial smoothing. As the canonical engineering artefact of mentalistic ACL semantics, FIPA-ACL is the negative example for Singh 1998, Wooldridge, Yolum & Singh, Fornara & Colombetti, and the public-semantics tradition generally. CBCL reuses the engineering of FIPA-ACL (typed performative envelope, conversation-id, ontology slot, protocol-id) while replacing the semantics with publicly verifiable commitment-based meaning. The modern LLM-agent protocol generation (Model Context Protocol, Agent-to-Agent Protocol, LACP) has retreated from FIPA’s level of semantic ambition; the open question is whether that retreat will repeat the mentalistic mistake under a new guise (sycophantic JSON tool-calls) or learn from the FIPA experience.

Mentalistic Semantics

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