AI协数学家：以智能体AI加速数学研究
AI协数学家是一个供数学家利用AI智能体进行开放式研究的工作平台。它针对数学工作流程的探索性与迭代性特点，提供从构思、文献检索、计算探索到定理证明的全方位支持。其异步、有状态的工作空间能管理不确定性、细化用户意图并追踪失败假设，模拟了人类协作模式。早期测试中，该系统已协助研究人员解决开放问题、识别新方向并发现被忽视的文献。在FrontierMath Tier 4等硬核问题求解基准测试中，AI协数学家取得了48%的最新最高分，展现了AI辅助数学发现的高度交互范式。
AI数学家终于不是吹牛了，FrontierMath Tier 4干到48%，还帮真人解决开放问题。搞数学和AI的都应该点开看看。
Authors:Daniel Zheng, Ingrid von Glehn, Yori Zwols, Iuliya Beloshapka, Lars Buesing, Daniel M. Roy, Martin Wattenberg, Bogdan Georgiev, Tatiana Schmidt, Andrew Cowie, Fernanda Viegas, Dimitri Kanevsky, Vineet Kahlon, Hartmut Maennel, Sophia Alj, George Holland, Alex Davies, Pushmeet Kohli
Abstract:We introduce the AI co-mathematician, a workbench for mathematicians to interactively leverage AI agents to pursue open-ended research. The AI co-mathematician is optimized to provide holistic support for the exploratory and iterative reality of mathematical workflows, including ideation, literature search, computational exploration, theorem proving and theory building. By providing an asynchronous, stateful workspace that manages uncertainty, refines user intent, tracks failed hypotheses, and outputs native mathematical artifacts, the system mirrors human collaborative workflows. In early tests, the AI co-mathematician helped researchers solve open problems, identify new research directions, and uncover overlooked literature references. Besides demonstrating a highly interactive paradigm for AI-assisted mathematical discovery, the AI co-mathematician also achieves state of the art results on hard problem-solving benchmarks, including scoring 48% on FrontierMath Tier 4, a new high score among all AI systems evaluated.
| Comments: | 23 pages; several citations added |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2605.06651 [cs.AI] |
| (or arXiv:2605.06651v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2605.06651 arXiv-issued DOI via DataCite |
Submission history
From: Daniel Roy [view email]
[v1]
Thu, 7 May 2026 17:56:32 UTC (667 KB)
[v2]
Wed, 13 May 2026 16:47:04 UTC (673 KB)
来源：HuggingFace Daily Papers（社区热门论文） · arxiv.org