aiqbench analysis
Choir introduces a novel protocol enabling distributed multi-agent systems to collaboratively formalize mathematical theorems across proof assistants like Lean and Isabelle. By allowing independent contributors to run their own agents while coordinating via a deterministic gate, it addresses the high computational costs and centralization issues inherent in current AI-driven formalization efforts. This development marks a significant step toward scalable, community-driven verification of complex logical systems using large language models.
Choir: An Open Protocol for Distributed Multi-Agent Autoformalization
arXiv:2609.31903v1 Announce Type: cross Abstract: AI agents can now formalize entire textbooks and major theorems in proof assistants such as Lean, but current efforts are typically centralized: a single team runs all agents and bears the full computational cost. We introduce Choir, an open protocol for distributed formalization. Choir decomposes a project into tasks that can be completed by independent contributors, each running their own agent with their own LLM subscription, while coordinating entirely through the project's GitHub repository. To support open participation, every contribution is checked by a deterministic gate before merge. Choir supports Lean 4, Isabelle, and Rocq, and is open source and modular, allowing projects to replace individual components or extend the protocol.
Abstract:AI agents can now formalize entire textbooks and major theorems in proof assistants such as Lean, but current efforts are typically centralized: a single team runs all agents and bears the full computational cost. We introduce Choir, an open protocol for distributed formalization. Choir decomposes a project into tasks that can be completed by independent contributors, each running their own agent with their own LLM subscription, while coordinating entirely through the project's GitHub repository. To support open participation, every contribution is checked by a deterministic gate before merge. Choir supports Lean 4, Isabelle, and Rocq, and is open source and modular, allowing projects to replace individual components or extend the protocol.
Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Logic in Computer Science (cs.LO); Multiagent Systems (cs.MA)
arXiv:2609.31903 [cs.AI]
(or arXiv:2609.31903v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2609.31903 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 217 words
Related coverage

[AINews] Meta Muse Wonder & Wonder Full: MSL’s Claude 5.5-tier Frontier Model
Latent Space · Oct 13, 2026

News
Quantum Computing Report · Jun 7, 2026
State of the Field: AI for Epistemics and Coordination
LessWrong · Oct 2, 2026

Govern AI agent tool access with Amazon Bedrock AgentCore Gateway
AWS · Aug 21, 2026