AI co-mathematician: Accelerating mathematicians with agentic AI

TL;DR

The paper presents the AI co-mathematician, an interactive AI system designed to support mathematicians in research, achieving state-of-the-art results on complex problem-solving benchmarks.

Contribution

It introduces a novel AI workbench that facilitates exploratory mathematical research and demonstrates high performance on challenging benchmarks.

Findings

Helped researchers solve open problems and find new research directions.

Achieved 48% score on FrontierMath Tier 4, a new high among AI systems.

Mirrors human collaborative workflows in mathematical discovery.

Abstract

We introduce the AI co-mathematician, a workbench for mathematicians to interactively leverage AI agents to pursue open-ended research. The AI co-mathematician is optimized to provide holistic support for the exploratory and iterative reality of mathematical workflows, including ideation, literature search, computational exploration, theorem proving and theory building. By providing an asynchronous, stateful workspace that manages uncertainty, refines user intent, tracks failed hypotheses, and outputs native mathematical artifacts, the system mirrors human collaborative workflows. In early tests, the AI co-mathematician helped researchers solve open problems, identify new research directions, and uncover overlooked literature references. Besides demonstrating a highly interactive paradigm for AI-assisted mathematical discovery, the AI co-mathematician also achieves state of the art results on hard problem-solving benchmarks, including scoring 48% on FrontierMath Tier 4, a new high score among all AI systems evaluated.