The process of scientific discovery relies on an interplay of observations, analysis, and hypothesis generation. Machine learning is increasingly being adopted to address individual aspects of this process. However, it remains an open challenge to fully automate the heuristic, iterative loop required to discover the laws of an unknown system by exploring it through experiments and analysis, without tailoring the approach to the specifics of a given task. Here, we introduce SciExplorer, an agent that leverages large language model tool-use capabilities to enable exploration of systems without any domain-specific blueprints, and apply it to physical systems that are initially unknown to the agent. We test SciExplorer on a broad set of models spanning mechanical dynamical systems, wave evolution, and quantum many-body physics. Despite using a minimal set of tools, primarily based on code execution, we observe impressive performance on tasks such as recovering equations of motion from observed dynamics and inferring Hamiltonians from expectation values. The demonstrated effectiveness of this setup opens the door towards similar scientific exploration in other domains, without the need for finetuning or task-specific instructions.

翻译：科学发现的过程依赖于观测、分析和假设生成之间的相互作用。机器学习正越来越多地被应用于解决这一过程的各个层面。然而，如何在不针对特定任务细节定制方法的情况下，通过实验和分析探索未知系统，从而完全自动化实现发现系统规律所需的启发式迭代循环，仍然是一个悬而未决的挑战。本文介绍 SciExplorer，这是一个利用大语言模型工具使用能力的智能体，使其能够在没有任何领域特定蓝图的情况下探索系统，并将其应用于智能体最初未知的物理系统。我们在涵盖机械动力系统、波演化以及量子多体物理的广泛模型集上测试了 SciExplorer。尽管仅使用了基于代码执行的最小工具集，我们观察到其在从观测动力学恢复运动方程、从期望值推断哈密顿量等任务上表现优异。该设置所展示的有效性为在其他领域进行类似的科学探索打开了大门，而无需进行微调或提供特定任务指令。