Towards Autonomous Mathematics Research
2026/02/10 by Tony Feng, Trieu H. Trinh, Garrett Bingham +25 · 19 voices · 1 citation
#cs.LG #cs.AI #cs.CL #cs.CY
paper · pdf
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.
Citations
Cited by
Discussions
- Towards Autonomous Mathematics Research [hn, 107 points, 53 comments]
- This is an interesting paper from. They describe a "thinking" agent that is able to do multiple rounds of revision to achieve significant goals in mathematical research. Q to @teorth.bsky.social, have [bsky, 2 points, 0 comments]
- arxiv.org/abs/2602.10177 pmc.ncbi.nlm.nih.gov/articles/PMC... www.sciencedaily.com/releases/202... Of course like you mention there is simply the broader sense pubs.rsna.org/journal/ai Covers [bsky, 1 points, 1 comments]
- Towards Autonomous Mathematics Research #HackerNews https://arxiv.org/abs/2602.10177 [bsky, 1 points, 0 comments]
- Pleased to find Google DeepMind staff reporting honestly: "... AI will become a tool that enhances rather than replaces mathematicians. ...natural language models struggle to reason reliably without h [bsky, 1 points, 1 comments]
- Towards Autonomous Mathematics Research (Google DeepMind) [hn, 1 points, 0 comments]
- Verso una ricerca matematica autonoma [lemmy, 1 points, 0 comments]
- There was extra training: "Building upon the key recipes developed for the IMO-gold model and incorporating a suite of novel technical improvements, we trained a stronger model, Gemini Deep Think (adv [bsky, 1 points, 1 comments]
- ⚡ Hackernews Top story: Towards Autonomous Mathematics Research [bsky, 0 points, 0 comments]
- https://arxiv.org/abs/2602.10177 AIエージェントAletheiaが数学研究を自律的に行います。 Gemini Deep Thinkを基盤とし、論文生成や未解決問題の解決にも成功しています。 人間とAIの協調により、数学研究の新たな地平を拓きます。 [bsky, 0 points, 0 comments]
- Towards Autonomous Mathematics Research https:// arxiv.org/abs/2602.10177 # arxiv [mastodon, 0 points, 0 comments]
- Though, the failure modes I observed seem to be still happening in these models as well. Here is an interesting paper by mathematician Tony Feng who has been responsible for building these models on t [bsky, 0 points, 0 comments]
- Towards Autonomous Mathematics Research https://arxiv.org/abs/2602.10177 (https://news.ycombinator.com/item?id=47026134) [bsky, 0 points, 0 comments]
- https://bsky.app/profile/buzzing.cc.web.brid.gy/post/3mey7y4cljbj2 [bsky, 0 points, 0 comments]
- Google DeepMind paper on the math they are doing arxiv.org/abs/2602.10177 [bsky, 0 points, 0 comments]
- Towards Autonomous Mathematics Research https://arxiv.org/abs/2602.10177 https://news.ycombinator.com/item?id=47026134 [bsky, 0 points, 0 comments]
- Towards Autonomous Mathematics Research https://arxiv.org/abs/2602.10177 [bsky, 0 points, 0 comments]
- Towards Autonomous Mathematics Research https://arxiv.org/abs/2602.10177 (https://news.ycombinator.com/item?id=47026134) [bsky, 0 points, 0 comments]
- ..https://arxiv.org/abs/2602.10177 (9/9) [bsky, 0 points, 0 comments]
Related