Multi-Agent Procedural Graph Extraction with Structural and Logical Refinement

/in /by

Publication Date: 3/29/2026

Event: The 19th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2026)

Reference: pp. 1-14, 2026

Authors: Wangyang Ying, Arizona State University; Yanchi Liu, NEC Laboratories America, Inc.; Xujiang Zhao, NEC Laboratories America, Inc.; Wei Cheng, NEC Laboratories America, Inc.; Zhengzhang Chen, NEC Laboratories America, Inc.; Wenchao Yu, NEC Laboratories America, Inc.; Yanjie Fu, Arizona State University; Haifeng Chen, NEC Laboratories America, Inc.

Abstract: 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 text2flow, 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 naturallanguage, 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 text2flow achieves substantial improvements in both structural correctness and logical consistency over strong baselines.

Publication Link: