[论文] Can LLMs Uncover Hidden Physical Laws through Free Exploration?

论文概要

研究领域: LLM / 科学发现 作者: Zhen Yang, Wen Wang, Xander Xu, Ying-Cong Chen 发布时间: 2026-10-27 arXiv: 2610.37649

中文摘要

科学发现往往始于一个意外的观察，从而引出新的研究问题。在一个物理定律被改变的世界里，LLM能否注意到意外行为（如重物下落更慢），并通过实验自主发现规律？为评估这一能力，本文引入LongChang——一个自动化框架，创造物理定律被改变的模拟世界。被评估的LLM作为探索者，操控物体、构建工具来调查自己提出的问题，无需研究任务提示或关于定律的暗示。独立的LLM智能体负责生成和审查场景、审查工具设计、评估报告的正确性和实验支持。探索记录引导场景演化以进行进一步探索，实现全流程无需人工干预。在12个LLM中，GPT-6-Astra以16.7%的发现率领先，其余11个全部0%。探索记录显示，大部分异常未被调查，物理定律的识别也仅部分完成。

原文摘要

Scientific discovery often begins with an unexpected observation that prompts a new research question. In a world with altered physical laws, can large language models (LLMs) notice unexpected behavior, such as heavier objects falling more slowly, and discover the law through experiments without being told what to investigate? To evaluate this ability, we introduce LongChang, an automated framework that creates simulated worlds with altered physics, where one or more laws differ from ordinary physics. The evaluated LLMs act as explorers, manipulating objects and building tools to investigate their own questions without research tasks or hints about these laws. Separate LLM agents generate and review scenes, review tool designs, and evaluate reports for correctness and experimental support using the altered physical laws and exploration records. These records guide scene evolution for further exploration, allowing the full cycle to run without human intervention. Among 12 LLMs, GPT-6-Astra achieves a discovery rate of 16.7%, while the other 11 score 0%. The exploration records reveal uninvestigated anomalies and only partial identification of the altered physical laws.

---

*自动采集于 2026-10-29*

#论文 #arXiv #AI #小凯