AI agents在无中心协作中自主发现5项数学新成果。
Autonomous Mathematical Discovery in an Open-World Multi-Agent Environment
- 多智能体自主探索、实验与合作，构建共享科学文献。
- 在5个问题上取得突破：如11维密接配置、卡基亚问题新解等。
- 不仅生成结果，还产出可解释的定理与证明，适合数学研究者跟进。
我们研究了在'Station'这一开放世界多智能体环境中，人工智能代理如何自主进行数学发现。这些来自不同模型家族的智能体在无中央协调或脚本流程的情况下，自行选择研究方向、开展实验、相互协作，并共同建立共享科学文献。在来自AlphaEvolve目录的12个构造问题及两个额外案例研究中，该系统在五个问题上取得了相对于已有文献的新成果：发现了新的有限域卡基亚集无限族、11维空间中604点的新精确密接构型、离散化卡基亚针问题和符号不确定性问题的新记录，以及埃拉多什最小重叠问题的显著改进下界。此外，代理还发现了书拉姆齐数的新无限族。重要的是，这些代理不仅产生数值构造，还生成了阐述其工作原理的定理与分析，使结果更具可解释性，便于数学家后续拓展。我们公开所有原始代理对话、证明与验证代码，提供这些发现生成过程的透明记录。
原文摘要 · Abstract (English)
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 build a shared scientific literature. Across 12 construction problems from the AlphaEvolve catalogue and two additional case studies, the Station obtained results novel relative to the prior literature on five problems: a new infinite family of finite-field Kakeya sets, new exact 604-point kissing configurations in dimension 11, new records 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. Importantly, the agents produced not only numerical constructions but also theorems and analyses explaining how those constructions work, making the results more interpretable and easier for mathematicians to build upon. We release all raw agent dialogues, proofs, and verification code, providing a transparent record of how these discoveries emerged.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。