Pact: A Choreographic Language for Agentic Ecosystems
This work addresses the problem of designing correct-by-construction protocols for multi-agent systems where participants may act in self-interest, which is crucial for open, untrusted environments like those enabled by LLM-based agents.
Pact introduces a choreographic programming language that incorporates game-theoretic operations to model agent self-interest, enabling protocol designers to reason about and compute decision policies for multi-party coordination with self-interested agents. A bounded-rational solver was implemented and applied to multi-party coordination scenarios.
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.