Large Language Models (LLMs) have garnered significant attention for several years now. Recently, their use as independently reasoning agents has been proposed. In this work, we test the potential of such agents for knowledge discovery in materials science. We repurpose LangGraph's tool functionality to supply agents with a black box function to interrogate. In contrast to process optimization or performing specific, user-defined tasks, knowledge discovery consists of freely exploring the system, posing and verifying statements about the behavior of this black box, with the sole objective of generating and verifying generalizable statements. We provide proof of concept for this approach through a children's parlor game, demonstrating the role of trial-and-error and persistence in knowledge discovery, and the strong path-dependence of results. We then apply the same strategy to show that LLM agents can explore, discover, and exploit diverse chemical interactions in an advanced Atomic Layer Processing reactor simulation using intentionally limited probe capabilities without explicit instructions.

翻译：大型语言模型（LLMs）多年来已获得广泛关注。近期，有研究提出将其作为具备自主推理能力的代理使用。本工作中，我们测试了此类代理在材料科学知识发现中的潜力。我们利用LangGraph的工具功能，为代理提供了一个可供探究的黑箱函数。与过程优化或执行特定用户定义任务不同，知识发现旨在自由探索系统，提出并验证关于该黑箱行为的陈述，其唯一目标是生成并验证可泛化的结论。我们通过一个儿童室内游戏为此方法提供了概念验证，展示了试错与坚持在知识发现中的作用，以及结果的强路径依赖性。随后，我们应用相同策略证明：在原子层处理先进反应器模拟中，即使仅使用有限探测能力且无明确指令，LLM代理仍能探索、发现并利用多样化的化学相互作用。