A software infrastructure proposal for mathematical research with AI agents
math.HO
Submitted: 2026-11-08
Updated: 2026-11-08
Comments: 16 pages, 8 figures, 2 tables. Prototype: https://github.com/stemma-math/stemma-exedra
Code: https://github.com/openai/math
Project page: https://stemma-math.github.io/stemma-exedra
License: http://creativecommons.org/licenses/by/4.0/
The gist: In 2026, AI agents began to produce mathematical results.
Terminology
Abstract
In 2026, AI agents began to produce mathematical results. They formalize complete theorems and settle open problems faster than a research group can review the results. The difficulty is shifting to organizing that output, deciding which results to trust and understanding them as a group. Current tools address particular problems or assist individual researchers, and none of them is designed as the shared working environment of a research group. We propose the design of a self-hosted environment in which a group of people and agents does its daily mathematical work. It consists of a small open core, which each group deploys with the resources it has and adapts through extensions. The core records who did what and gives every message and result a stable address. We also outline how the formal libraries of different groups, maintained mostly by agents, can form a network. We describe Stemma, an early prototype that implements part of the proposal, and illustrate it with a synthetic example.
Sources
- Prove2Me: An Open Collaborative Platform for Scaling Math Formalization
- Resolution of Erd\H{o}s Problem #728: a writeup of Aristotle's Lean proof
- The crisis of AI-generated mathematics
- LeanMarathon: Toward Reliable AI Co-Mathematicians through Long-Horizon Lean Autoformalization
- Stellar Colosseum: A Many-Agent Harness for Long-Horizon Research in Mathematics and Theoretical Computer Science
- MathCoPilot: An Interactive System for Human-AI Symbiotic Paradigm of Mathematical Research
- AI co-mathematician: Accelerating mathematicians with agentic AI