Multi-agent system achieves novel mathematical discoveries including new Kakeya sets
Stephen Chung · hf · 2026-08-27
This paper studies autonomous mathematical discovery in the "Station," an open-world multi-agent environment where AI agents pursue shared goals without central coordination. Across 12 construction problems, agents achieved novel results on five, including new infinite families of finite-field Kakeya sets, new exact 604-point kissing configurations in dimension 11, and improved bounds for Erdős's minimum-overlap problem. Agents produced not just numerical constructions but also theorems and analyses explaining them. All raw dialogues, proofs, and verification code are released.
Related event: Multi-Agent Environment The Station Achieves Autonomous Math Research(2 posts)→
More from Research
- Interpretability paper incoming: in-depth look at testing explanations on modern LLMs — burny_tech · 2026-10-16
- Ex-OpenAI interpretability lead: neurons in trillion-param models are mostly legible now — CatAstro_Piyush · 2026-10-16
- Better-learning models tend to be more interpretable, argues Nick Cammarata — burny_tech · 2026-10-16
- MIT let Claude Code loose on a virtual island: it played for 30 hours with no task — CatAstro_Piyush · 2026-10-16
- Cornell and Amazon revisit the 16x pretraining compute gap: diffusion LMs need only 3-8x — LucaAmb · 2026-10-16
- AI trained on the fraction of human intelligence that fit the page — r0ck3t23 · 2026-10-16