Towards Autonomous Mathematics Research

2026-02-10

AI Summary

This work aims to advance artificial intelligence from competition-level problem solving toward autonomous mathematical research, encompassing literature comprehension, long-horizon proof construction, and open-problem resolution. We introduce Aletheia, a mathematical research agent built upon the Gemini Deep Think enhanced reasoning architecture, integrating law-of-thought expansion at inference time, dense tool invocation mechanisms, and an end-to-end pipeline for natural-language proof generation and verification. Aletheia produces the first fully AI-generated mathematics research paper, establishes quantitative metrics for assessing autonomy and novelty of results, and introduces “human-AI interaction cards” to enhance collaborative transparency. The system autonomously generated a paper on structural constants of eigenweights in arithmetic geometry, co-proved bounds on independent sets in particle systems, and resolved four open problems from Bloom’s Erdős conjecture database.

Technology Category

• Knowledge Representation and Reasoning: Automated Reasoning and Theorem Proving
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications

Abstract

Recent advances in foundational models have yielded reasoning systems capable of achieving a gold-medal standard at the International Mathematical Olympiad. The transition from competition-level problem-solving to professional research, however, requires navigating vast literature and constructing long-horizon proofs. In this work, we introduce Aletheia, a math research agent that iteratively generates, verifies, and revises solutions end-to-end in natural language. Specifically, Aletheia is powered by an advanced version of Gemini Deep Think for challenging reasoning problems, a novel inference-time scaling law that extends beyond Olympiad-level problems, and intensive tool use to navigate the complexities of mathematical research. We demonstrate the capability of Aletheia from Olympiad problems to PhD-level exercises and most notably, through several distinct milestones in AI-assisted mathematics research: (a) a research paper (Feng26) generated by AI without any human intervention in calculating certain structure constants in arithmetic geometry called eigenweights; (b) a research paper (LeeSeo26) demonstrating human-AI collaboration in proving bounds on systems of interacting particles called independent sets; and (c) an extensive semi-autonomous evaluation (Feng et al., 2026a) of 700 open problems on Bloom's Erdos Conjectures database, including autonomous solutions to four open questions. In order to help the public better understand the developments pertaining to AI and mathematics, we suggest quantifying standard levels of autonomy and novelty of AI-assisted results, as well as propose a novel concept of human-AI interaction cards for transparency. We conclude with reflections on human-AI collaboration in mathematics and share all prompts as well as model outputs at https://github.com/google-deepmind/superhuman/tree/main/aletheia.

Problem

• autonomous mathematics research
• AI-assisted theorem proving
• open problem solving
• mathematical reasoning
• human-AI collaboration

Innovation

• mathematical reasoning agent
• inference-time scaling law
• autonomous theorem proving
• AI-assisted research
• human-AI collaboration