Pact: A Choreographic Language for Agentic Ecosystems

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gopinathan, Kiran, Feser, Jack, Naim, Michelangelo, Tavares, Zenna, Bingham, Eli
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913088651919360
author Gopinathan, Kiran
Feser, Jack
Naim, Michelangelo
Tavares, Zenna
Bingham, Eli
author_facet Gopinathan, Kiran
Feser, Jack
Naim, Michelangelo
Tavares, Zenna
Bingham, Eli
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2605_03143
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Pact: A Choreographic Language for Agentic Ecosystems
Gopinathan, Kiran
Feser, Jack
Naim, Michelangelo
Tavares, Zenna
Bingham, Eli
Programming Languages
Artificial Intelligence
Distributed, Parallel, and Cluster Computing
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.
title Pact: A Choreographic Language for Agentic Ecosystems
topic Programming Languages
Artificial Intelligence
Distributed, Parallel, and Cluster Computing
url https://arxiv.org/abs/2605.03143