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.

Original post →

More from Research

Research channel →