Pact: A Choreographic Language for Agentic Ecosystems

2026-05-04

AI Summary

Existing choreographic programming approaches assume fully cooperative participants and struggle to handle deviations by self-interested agents in open environments. This work proposes Pact, a novel language that integrates agent preferences and decision-making mechanisms from game theory into choreographic programming for the first time. By formalizing protocols as game-theoretic models, Pact explicitly captures self-interested behavior. Coupled with a bounded-rationality solver, Pact enables automatic computation and rational analysis of multi-agent strategies. Experimental results demonstrate that the approach effectively models coordination scenarios involving self-interested agents and ensures that protocols are rationally adhered to under strategic equilibria.

Abstract

Recent advances in large language models have led to the rise of software systems (i.e. agents) that execute with increasing autonomy on behalf of users in open, multi-party settings, interacting with untrusted counterparts and managing private information. Choreographic programming offers correct-by-construction protocol-design for such settings, but assumes cooperative participants -- it has no notion of agent self-interest, that is, why an agent will follow a protocol. In this talk we introduce Pact, a choreographic language extended with operations to describe agent choices and preferences, drawing from the rich literature of game theory. Every Pact protocol maps to a formal game, allowing protocol designers to reason about game-theoretic properties of their protocols, such as solving for decision policies. We present Pact's design and a preliminary implementation -- a bounded-rational solver that computes decision policies over Pact protocols -- and findings from applying this language to multi-party coordination with self-interested agentic participants.

Problem

• choreographic programming
• agent self-interest
• multi-party coordination
• game theory
• autonomous agents

Innovation

• choreographic programming
• game theory
• self-interested agents
• protocol design
• decision policies