arXiv cs.AI· Yuxiao Hu, Qian Li, Ding Wang, Siheng Chen, Linfeng Zhang, Jinyue Yan, Yuntian Chen·· 11 小时前AI 评分31
SCOPE 框架与 ClosureBench 基准：从方程搜索转向猜想驱动的科学发现
Beyond Equation Search: Conjecture-Guided Discovery with SCOPE and ClosureBench
AI 导读
SCOPE 是一个维持多条猜想驱动研究轨迹的框架，多个科学家智能体独立通过方程建模、问题构建和主动实验推进猜想，再交换证据修正研究方向并汇总为关联模型、结论与证据的科学报告。
正文 · 原文
Abstract:Most symbolic regression methods optimize candidate equations, but improving an equation's fit does not establish whether its underlying scientific conjecture should be retained, revised, or rejected. A conjecture may admit multiple mathematical realizations, and similarly accurate equations may imply different explanations. This motivates a shift from refining individual expressions to developing and testing the conjectures that guide them. We introduce SCOPE, a framework that sustains multiple conjecture-driven research trajectories. Multiple scientist agents independently pursue conjectures through equation modeling, question formulation, and active experimentation, then exchange evidence to revise their conjectures and research directions. Their findings are consolidated into a scientific report linking models, conclusions, and evidence. Existing equation-discovery benchmarks primarily assess recovered expressions, leaving the evidence and scientific conclusions established through the investigation underexamined. We therefore introduce ClosureBench, an interactive benchmark of 60 closure-discovery tasks across five scientific domains. ClosureBench focuses on closure-discovery tasks to give equation discovery a concrete scientific purpose. Each task embeds an unknown algebraic relation in a known PDE system, where agents control experimental conditions in OpenFOAM to acquire new data for equation discovery. Beyond equation accuracy, ClosureBench proposes three metrics to evaluate the discovery process: evidence faithfulness, mechanism insight, and experimental effectiveness. Compared with diverse baselines, SCOPE achieves higher equation accuracy on both ClosureBench and a real-world scientific discovery case, while producing more accurate, reliable, and effective scientific discoveries.
| Subjects: | Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.18938 [cs.AI] |
| (or arXiv:2610.18938v3 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.18938 arXiv-issued DOI via DataCite |
Submission history
From: Yuxiao Hu [view email]
[v1]
Tue, 13 Oct 2026 12:46:49 UTC (753 KB)
[v2]
Mon, 2 Nov 2026 07:31:34 UTC (754 KB)
[v3]
Thu, 5 Nov 2026 05:42:31 UTC (754 KB)
来源：arXiv cs.AI · arxiv.org