Paperlane

no. 12 · Tuesday 10 November 2026

A software infrastructure proposal for mathematical research with AI agents

Mario Vago Marzal and Enric Cosme Llópez

math.HO · code · ∎ lean 3 sorry · 16 pp

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.

code
github.com/stemma-math/stemma-exedra ∎ Lean project (lean/fixture/lakefile.toml, lean/fixture/lean-toolchain) builds with 3 sorry warnings at 937cbba, checked 2026-11-10 build details
comments
16 pages, 8 figures, 2 tables. Prototype: https://github.com/stemma-math/stemma-exedra
fields
History and Overview
pdf ↗ page arXiv:2611.11645 ↗