Metraipolis › archive › dc_f31d84fa8760

Autonomous Mathematical Discovery in an Open-World Multi-Agent Environment — arXiv:2608.23691

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.23691
License (as archived)
CC0-1.0
Archived
2026-10-18T06:13:52.101Z
SHA-256 of the archived text
648f2ab0b6f55ea2283e59db69066450cd972ecabd9b52858af0d3c6d56d55a0
Stable URL of this page
https://metraipolis.com/documento/dc_f31d84fa8760

How to cite

Autonomous Mathematical Discovery in an Open-World Multi-Agent Environment — arXiv:2608.23691 — arXiv (en), https://arxiv.org/abs/2608.23691 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f31d84fa8760 (Metraipolis archive dc_f31d84fa8760, sha256 648f2ab0b6f55ea2283e59db69066450cd972ecabd9b52858af0d3c6d56d55a0)
BibTeX
@misc{dcf31d84fa8760,
  title = {Autonomous Mathematical Discovery in an Open-World Multi-Agent Environment — arXiv:2608.23691},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.23691},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f31d84fa8760; sha256 648f2ab0b6f55ea2283e59db69066450cd972ecabd9b52858af0d3c6d56d55a0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.23691. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We study autonomous mathematical discovery in the Station, an open-world multi-agent environment in which AI agents from different model families pursue a shared research goal without a central coordinator or scripted pipeline. Agents choose their own research directions, conduct experiments, collaborate and publish papers. These papers accumulate into a shared body of knowledge that later agents can read, cite and extend. We evaluated the Station on 12 mathematical construction problems from the AlphaEvolve study and two additional case studies. Five of the 12 problems yielded results novel relative to the prior literature: a new infinite family of finite field Kakeya sets, new exact 604-point kissing configurations in eleven dimensions, improved bounds for the discretized Kakeya needle and sign uncertainty problems, and a substantially improved lower bound for Erdős's minimum overlap problem. Agents also discovered novel infinite families for Book Ramsey numbers. Their research extended beyond searching for high-scoring constructions: agents developed explanations of their findings and proved theorems outside the assigned tasks. These explanations guided further discoveries and were preserved in the agents' papers, making the underlying insights easier for external researchers to understand and build upon. All presented discoveries are supported by exact constructions or proofs formally verified in Lean. We release the source code, full agent dialogues, papers and verification code, providing a transparent record of how these discoveries emerged.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-26 in cs.MA).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Discrete Mathematics (cs.DM); Multiagent Systems (cs.MA).
Pagina del lavoro: https://arxiv.org/abs/2608.23691 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-18T06:07:44.725Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-08-26?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).