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.
More from Research
- GLM-5.3-Flash Released: 1M Context & Open Weights — qinzytech · 2026-08-27
- Research predicts optimal model size and data allocation for pre-training — yoavgo · 2026-08-27
- Experts debate if RMSNorm helps interpret neural network black boxes — CFGeek · 2026-08-27
- ARC-AGI-3 learnings: Key designs for self-learning AI agents — GregKamradt · 2026-08-27
- Recommended Reads: Poggio on Minds & Machines, Welling on GenAI Thermodynamics — neurovium · 2026-08-27
- Category Theory Master: AI Expands Mathematical Truth but Doesn't Change Core — begusgasper · 2026-08-27