Ansatz 与 Ansatze：面向 AI 辅助数学发现的持续图记忆与社区平台
Continual Graph Memory and Community Infrastructure for AI-Assisted Mathematical Discovery
作者提出 Ansatz 研究框架与 Ansatze 社区平台，用持续图记忆把模型接受的结论与依赖同人工整理探索分开记录，支持检视、引导和检查数学研究工作。在 First Proof 上，Ansatz 在两个各含十道题的批次中均记录到九次本地验证器闭合，第二批的一个部分结果也按该研究标准计为通过；这些由模型评估的结果包含持续搜索，与专家验证不同。
Authors:Eric Hanchen Jiang, Junyi Zhang, Jinxi Yu, Jiachen Lu, Zhi Zhang, Michael Simon, Justin Baker, Richard Cai, Sneha Agarwal, Yubei Li, Hyunsik Chae, Xinjie He, Kyle Zheng, Vigyan Sahai, Ethan Ji, Alexander K Taylor, Yiwen Kou, Kyle Hess, Xiao Liang, Yingnian Wu, J.D. Zamfirescu-Pereira, Andrea Bertozzi, Kai-Wei Chang, Eunice Jun, Raghu Meka, Nanyun Peng, Amit Sahai, Matthew Sottile, Terence Tao, Wei Wang
Abstract:Mathematical discovery requires preserving partial ideas and the evidence supporting their reuse. We present Ansatz, a research harness whose continual graph memory separates model-accepted claims and dependencies from curated exploration, and Ansatze, a community platform for inspecting, guiding and checking this work. On First Proof, Ansatz recorded nine local verifier closures in each of two ten-problem batches; a partial result in the Second Batch also counted as a pass under the study's criterion. These model-assessed outcomes include continued searches and differ from expert validation. Component studies and re-review expose disagreements and their dependency reach. Open-problem investigations produced candidate results, with five Lean formalizations reported. The platform connects problem discovery, research records, manuscript analysis and formal checking while preserving distinct evidence states. Together, these systems support cumulative human-AI research through persistent investigation and inspectable contributions.
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.02945 [cs.AI] |
| (or arXiv:2610.02945v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.02945 arXiv-issued DOI via DataCite |
Submission history
From: Eric Jiang [view email]
[v1]
Fri, 2 Oct 2026 07:38:09 UTC (1,271 KB)
[v2]
Fri, 6 Nov 2026 17:44:13 UTC (9,753 KB)
来源：arXiv cs.CL · arxiv.org