Choir: An Open Protocol for Distributed Multi-Agent Autoformalization
cs.AI, cs.CL, cs.LO, cs.MA
Submitted: 2026-09-25
Updated: 2026-09-25
Code: https://github.com/yidiq7/Pr
License: http://creativecommons.org/licenses/by/4.0/
The gist: 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
Terminology
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.
Sources
- HepLean: Digitalising high energy physics
- CSLib: The Lean Computer Science Library
- Automatic Textbook Formalization
- Formalizing Mathematics at Scale
- M2F: Automated Formalization of Mathematical Literature at Scale
- Formalizing Numerical Analysis: An Agent Pipeline and Quality Audit Beyond Kernel Acceptance
- Munkres' General Topology Autoformalized in Isabelle/HOL
- 130k Lines of Formal Topology in Two Weeks: Simple and Cheap Autoformalization for Everyone?
- Progress in Formalizing Sphere Packing in Dimension 8
- Prove2Me: An Open Collaborative Platform for Scaling Math Formalization
- The Equational Theories Project: Advancing Collaborative Mathematical Research at Scale
- LeanMarathon: Toward Reliable AI Co-Mathematicians through Long-Horizon Lean Autoformalization
- Long-horizon autoformalization of a core theorem underlying MIP* = RE
- Automated Conjecture Resolution with Formal Verification
- MerLean: An Agentic Framework for Autoformalization in Quantum Computation
- Multi-agent Autoformalization of Tensor Network Theory
- Beyond the Library: An Agentic Framework for Autoformalizing Research Mathematics
- Lean Pool: An AI-Maintained Archive of Formalized Mathematics
- Agent Hunt: Bounty Based Collaborative Autoformalization With LLM Agents
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems