用大模型系统解决8个数学难题，5个自主完成，6个可发表。
Bolzano: Case Studies in LLM-Assisted Mathematical Research
- 多智能体协作+持续知识库，自动迭代推理与验证。
- 8个问题中6个达到可发表水平，5个基本由系统自主完成。
- 为大模型参与科研提供实证，适合研究人机协作的学者。
我们报告了通过Bolzano——一个开源的多智能体大语言模型系统——协助解决的八个数学与理论计算机科学问题的新成果。Bolzano在多轮交互中协调并行证明智能体与验证智能体，并维护跨轮次持续的知识库。根据Feng等人的显著性-自主性分类体系，八项结果中有六项达到可发表研究水平，五项由Bolzano基本自主完成。这些结果为大模型在数学研究中的实质性贡献提供了证据，呼应了Bubeck、Woodruff等人近期的研究报告。
原文摘要 · Abstract (English)
We report new results on eight problems in mathematics and theoretical computer science, produced with the assistance of Bolzano, an open-source multi-agent LLM system. Bolzano orchestrates rounds of interaction between parallel prover agents and a verifier agent while maintaining a persistent knowledge base that is carried across rounds. Classified using the significance-autonomy taxonomy of Feng et al., six of the eight results reach the level of publishable research, and five of the eight were produced essentially autonomously by Bolzano. Our results provide evidence that LLMs can contribute meaningfully to mathematical research, complementing recent reports by Bubeck et al., Woodruff et al., and others.
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。