Multi-Agent Procedural Graph Extraction with Structural and Logical Refinement
This addresses the underexplored challenge of procedural graph extraction for applications requiring interpretable and controllable refinement, though it is incremental as it builds on existing LLM capabilities.
The paper tackles the problem of automatically extracting workflows as procedural graphs from natural language, which often results in ill-formed structures or logical misalignments with LLMs, and presents a multi-agent framework that achieves substantial improvements in structural correctness and logical consistency over strong baselines.
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.