用多智能体迭代优化，让大模型更准地从文本提取流程图。
Multi-Agent Procedural Graph Extraction with Structural and Logical Refinement
- 分三阶段：建图、结构诊断、语义对齐，逐步修正错误。
- 在结构正确性和逻辑一致性上显著优于现有方法。
- 无需调参或监督，适合需要可解释性的复杂流程建模。
从自然语言中自动提取流程图为程序图具有前景但研究不足，需兼顾结构有效性与逻辑一致性。尽管近期大语言模型（LLMs）在流程图提取方面展现出潜力，但常产生结构不良或逻辑误解。我们提出 exttt{Model}，一种多智能体框架，将流程图提取视为多轮推理过程，并包含专门的结构与逻辑修正机制。该框架迭代三个阶段：(1) 图构建智能体执行图提取；(2) 模拟智能体诊断并解释结构缺陷；(3) 语义智能体对齐流程逻辑与源文本的语言线索。重要反馈以自然语言形式注入后续提示，实现可解释且可控的优化。模块化设计使各智能体能针对性修复特定错误类型，无需监督或参数更新。实验表明， exttt{Model} 在结构正确性与逻辑一致性上均显著优于强基线。
原文摘要 · Abstract (English)
Automatically extracting workflows as procedural graphs from natural language is promising yet underexplored, demanding both structural validity and logical alignment. While recent large language models (LLMs) show potential for procedural graph extraction, they often produce ill-formed structures or misinterpret logical flows. We present \model{}, a multi-agent framework that formulates procedural graph extraction as a multi-round reasoning process with dedicated structural and logical refinement. The framework iterates through three stages: (1) a graph extraction phase with the graph builder agent, (2) a structural feedback phase in which a simulation agent diagnoses and explains structural defects, and (3) a logical feedback phase in which a semantic agent aligns semantics between flow logic and linguistic cues in the source text. Important feedback is prioritized and expressed in natural language, which is injected into subsequent prompts, enabling interpretable and controllable refinement. This modular design allows agents to target distinct error types without supervision or parameter updates. Experiments demonstrate that \model{} achieves substantial improvements in both structural correctness and logical consistency over strong baselines.
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。