用信息论框架让多个AI agent按科学原理高效探索，减少盲目试错。
PiFlow: Principle-Aware Scientific Discovery with Multi-Agent Collaboration
- 基于信息论设计原则约束的多智能体协作流程，确保假设与证据关联。
- 在三个领域实验中，发现效率提升31.18%~41.73%，解质量提高12.47%~31.72%。
- 可插拔集成现有架构，加速求解5.6倍，同时减少27%的计算消耗。
基于大语言模型的多智能体系统（MAS）在科学发现中展现出巨大潜力。然而，现有方法常依赖预设工作流，缺乏理性约束，导致盲目假设和假设与证据脱节，阻碍不确定性系统性降低。克服这一问题需引入原则性探索机制。本文提出PiFlow，一种信息论驱动的框架，将自动化科学发现视为受科学定律等原则引导的不确定性缩减过程。在三个不同科学领域的广泛评估表明，PiFlow相比顶尖方法：(I) 发现效率提升31.18%~41.73%，解质量提升12.47%~31.72%；(II) 求解速度加快5.6倍，令牌消耗最多减少27%；(III) 可作为即插即用模块，适配并提升现有智能体架构。整体上，PiFlow确立了高效智能体科学发现的新范式，为更稳健、快速的AI驱动研究铺平道路。
原文摘要 · Abstract (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 the systematic reduction of uncertainty. Overcoming these limitations fundamentally requires a principled approach to exploration. We introduce PiFlow, an information-theoretical framework, treating automated scientific discovery as a structured uncertainty reduction problem guided by principles (e.g., scientific laws). Extensive evaluations across three distinct scientific domains demonstrate that PiFlow (I) improves discovery efficiency by 31.18%~41.73% and solution quality by 12.47%~31.72% against state-of-the-art methods, (II) delivers a 5.6x speedup in time-to-solution while reducing token consumption by up to 27% compared to vanilla agents, and (III) serves as a Plug-and-Play module that generalizes on existing agent architecture. Overall, PiFlow establishes a novel paradigm shift in highly efficient agentic scientific discovery, paving the way for more robust and accelerated AI-driven research.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。