arXiv cs.AI· Anita Yang, Siu Lun Chau, Tomoya Wakayama, Krikamol Muandet, Masaki Adachi·· 9 天前AI 评分22
用可能性推理实现开放式科学发现
Open-ended Scientific Discovery with Possibilistic Reasoning
AI 导读
研究将开放式科学发现问题形式化为溯因自主科学发现（AASD），基于可能性理论提出可计算的溯因效用度量，并给出首个 AASD 算法 possibility frontier search，在合适条件下保持 anytime 有效性并渐近达到 ε-最优溯因效用。合成与真实科学发现任务实验显示其表现强劲。
正文 · 原文
Abstract:Autonomous scientific discovery with LLMs requires generating and testing hypotheses adaptively as evidence accumulates while maintaining statistical validity. Existing anytime-valid methods can handle data-dependent hypotheses, but open-ended discovery poses a deeper challenge: the best discovered hypothesis may still be the best of a bad lot, with better explanations yet undiscovered, while even background knowledge such as physical laws may require revision in light of new findings. In response, we formalize the problem as Abductive Autonomous Scientific Discovery (AASD) using possibility theory. We introduce abductive utility, a computable measure of discovery progress, and possibility frontier search, the first algorithm for AASD, which maintains anytime validity and achieves $\varepsilon$-optimal abductive utility asymptotically under suitable conditions. Experiments on synthetic and real-world scientific-discovery tasks show strong performance.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.11289 [cs.AI] |
| (or arXiv:2610.11289v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.11289 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Anita Yang [view email]
[v1]
Thu, 8 Oct 2026 05:52:14 UTC (1,714 KB)
来源：arXiv cs.AI · arxiv.org