mlsanityData to 7 Oct 2026

Multi-Agent Procedural Graph Extraction with Structural and Logical Refinement

arXiv 2601.19170 ↗First posted 27 Jan 2026cs.AIcited by 0

On the map: LLM agents and tool use → Web, search, and research agents

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. Builds on 24 of its 50 references that are in the map. First posted on arXiv 27 Jan 2026.

Builds on

24 of 50 references.

References · 24

  1. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  2. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  3. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
  4. 2023Unifying Large Language Models and Knowledge Graphs: A Roadmapcited by 663
  5. 2020A Survey on Knowledge Graphs: Representation, Acquisition and Applicationscited by 643
  6. 2016End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRFcited by 341
  7. 2020A Dataset for Tracking Entities in Open Domain Procedural Textcited by 37
  8. 2023Self-optimizing Feature Generation via Categorical Hashing Representation and Hierarchical Reinforcement Crossingcited by 30
  9. 2024Evolutionary Large Language Model for Automated Feature Transformationcited by 29
  10. 2024Feature Selection as Deep Sequential Generative Learningcited by 21
  11. 2024Unsupervised Generative Feature Transformation via Graph Contrastive Pre-training and Multi-objective Fine-tuningcited by 21
  12. 2022PET: An Annotated Dataset for Process Extraction from Natural Language Textcited by 15
12 more
  1. 2025CT-PatchTST: Channel-Time Patch Time-Series Transformer for Long-Term Renewable Energy Forecastingcited by 15
  2. 2022Title2Event: Benchmarking Open Event Extraction with a Large-scale Chinese Title Datasetcited by 14
  3. 2024Neuro-Symbolic Embedding for Short and Effective Feature Selection via Autoregressive Generationcited by 13
  4. 2024Revolutionizing Biomarker Discovery: Leveraging Generative AI for Bio-Knowledge-Embedded Continuous Space Explorationcited by 11
  5. 2024Topology-aware Reinforcement Feature Space Reconstruction for Graph Datacited by 11
  6. 2021Constructing Flow Graphs from Procedural Cybersecurity Textscited by 8
  7. 2024Set-Aligning Framework for Auto-Regressive Event Temporal Graph Generationcited by 8
  8. 2025Efficient Post-Training Refinement of Latent Reasoning in Large Language Modelscited by 7
  9. 2024PAGED: A Benchmark for Procedural Graphs Extraction from Documentscited by 4
  10. 2022Leveraging pre-trained language models for conversational information seeking from textcited by 3
  11. 2024Cascading Large Language Models for Salient Event Graph Generationcited by 3
  12. 2025Data-Efficient Symbolic Regression via Foundation Model Distillationcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Scalable and Accurate Graph Reasoning with LLM-based Multi-Agents
  2. 2025Unifying Language Agent Algorithms with Graph-based Orchestration Engine for Reproducible Agent Research
  3. 2026GraphDC: A Divide-and-Conquer Multi-Agent System for Scalable Graph Algorithm Reasoning
  4. 2026GRAIN: Bridging Name and Narrative Shifts in Real-World Graph Reasoning through Invariance-Rewarded Agentic RL
  5. 2026GTA: Graph Theory Agent and Benchmark for Algorithmic Graph Reasoning with LLMs
  6. 2026Procedural Graphs: Self-Evolving Execution Structures for LLM Agents
  7. 2025Graph Counselor: Adaptive Graph Exploration via Multi-Agent Synergy to Enhance LLM Reasoning
  8. 2025GraphMaster: Automated Graph Synthesis via LLM Agents in Data-Limited Environments