PiFlow：基于多智能体协作的原则感知科学发现

PiFlow: Principle-aware Scientific Discovery with Multi-Agent Collaboration

May 21, 2025

作者: Yingming Pu, Tao Lin, Hongyu Chen

cs.AI

摘要

基于大型语言模型（LLM）的多智能体系统（MAS）在科学发现领域展现出显著潜力。然而，现有方法通常采用缺乏合理性约束的预定义工作流来自动化科学发现，这往往导致无目的的假设生成，并难以将假设与证据系统性地关联起来，从而阻碍了系统性的不确定性降低。从根本上克服这些限制，需要系统性地减少不确定性。我们提出了PiFlow，一个信息理论框架，将自动化科学发现视为一个由科学定律等原则指导的结构化不确定性降低问题。在三个不同科学领域的评估中——发现具有目标特性的纳米材料结构、生物分子和超导体候选材料——我们的方法显著提高了发现效率，表现为属性值与探索步骤的曲线下面积（AUC）增加了73.55%，并且与基础智能体系统相比，解决方案质量提升了94.06%。总体而言，PiFlow作为一种即插即用方法，为高效自动化科学发现建立了新的范式转变，为更稳健和加速的AI驱动研究铺平了道路。代码已公开在我们的GitHub仓库：https://github.com/amair-lab/PiFlow。

English

Large Language Model (LLM)-based multi-agent systems (MAS) demonstrate remarkable potential for scientific discovery. Existing approaches, however, often automate scientific discovery using predefined workflows that lack rationality constraints. This often leads to aimless hypothesizing and a failure to consistently link hypotheses with evidence, thereby hindering systematic uncertainty reduction. Overcoming these limitations fundamentally requires systematic uncertainty reduction. We introduce PiFlow, an information-theoretical framework, treating automated scientific discovery as a structured uncertainty reduction problem guided by principles (e.g., scientific laws). In evaluations across three distinct scientific domains -- discovering nanomaterial structures, bio-molecules, and superconductor candidates with targeted properties -- our method significantly improves discovery efficiency, reflected by a 73.55\% increase in the Area Under the Curve (AUC) of property values versus exploration steps, and enhances solution quality by 94.06\% compared to a vanilla agent system. Overall, PiFlow serves as a Plug-and-Play method, establishing a novel paradigm shift in highly efficient automated scientific discovery, paving the way for more robust and accelerated AI-driven research. Code is publicly available at our https://github.com/amair-lab/PiFlow{GitHub}.