mlsanityData to 14 Oct 2026

REGREACT: Self-Correcting Multi-Agent Pipelines for Structured Regulatory Information Extraction

arXiv 2604.12054 ↗First posted 13 Apr 2026cs.MAcited by 0

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

Abstract (arXiv)

Extracting structured, machine-readable compliance criteria from regulatory documents remains an open challenge. Single-pass language models hallucinate structural elements, lose hierarchical relationships, and fail to resolve inter-document dependencies. We introduce textscRegReAct, a self-correcting multi-agent framework that decomposes regulatory information extraction into seven specialized stages, each with an textitObserve--Diagnose--Repair (ODR) loop that validates outputs against the source, correcting not only model hallucinations but also cross-reference errors in the regulations themselves. To ensure structural accuracy, textscRegReAct constructs a typed criterion graph; to ensure completeness, it resolves external dependencies by retrieving, summarizing, and embedding referenced legal content inline, producing self-contained outputs. Applying textscRegReAct to three EU Taxonomy Delegated Acts, we construct a dataset comprising 242 activities with over 4,800 hierarchical criteria, thresholds, and enriched source summaries. Evaluation against a GPT-4o single-pass baseline confirms that textscRegReAct outperforms it across all structural and semantic metrics. Code and data will be made publicly available: https://github.com/RECOR-Benchmark/RECOR

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. Builds on 29 of its 66 references that are in the map. First posted on arXiv 13 Apr 2026.

Builds on

29 of 66 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025AgenticIE: An Adaptive Agent for Information Extraction from Complex Regulatory Documents15 Sep

Other references · 28

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  4. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  5. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,988
  6. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  7. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,453
  8. 2020ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERTcited by 1,178
  9. 2023Large Language Models Cannot Self-Correct Reasoning Yetcited by 1,017
  10. 2016Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphscited by 861
  11. 2023CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquingcited by 783
  12. 2021LexGLUE: A Benchmark Dataset for Legal Language Understanding in Englishcited by 310
16 more
  1. 2022Generating Sequences by Learning to Self-Correctcited by 277
  2. 2024MinerU: An Open-Source Solution for Precise Document Content Extractioncited by 267
  3. 2023Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategiescited by 238
  4. 2021CUAD: An Expert-Annotated NLP Dataset for Legal Contract Reviewcited by 236
  5. 2020How Does NLP Benefit Legal System: A Summary of Legal Artificial Intelligencecited by 129
  6. 2023Can GPT-3 Perform Statutory Reasoning?cited by 73
  7. 2023LEXTREME: A Multi-Lingual and Multi-Task Benchmark for the Legal Domaincited by 68
  8. 2021GenIE: Generative Information Extractioncited by 53
  9. 2021MarkupLM: Pre-training of Text and Markup Language for Visually-rich Document Understandingcited by 45
  10. 2022WebFormer: The Web-page Transformer for Structure Information Extractioncited by 34
  11. 2025GraphCompliance: Structure-Aware Regulatory Compliance through Policy-Context Graph Alignmentcited by 9
  12. 2026RECOR: Reasoning-focused Multi-turn Conversational Retrieval Benchmarkcited by 6
  13. 2025SustainableQA: A Comprehensive Question Answering Dataset for Corporate Sustainability and EU Taxonomy Reportingcited by 5
  14. 2025Towards Trustworthy Legal AI through LLM Agents and Formal Reasoningcited by 5
  15. 2025Executable Governance for AI: Translating Policies into Rules Using LLMscited by 3
  16. 2025Automated Analysis of Sustainability Reports: Using Large Language Models for the Extraction and Prediction of EU Taxonomy-Compliant KPIscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026De Jure: Iterative LLM Self-Refinement for Structured Extraction of Regulatory Rules
  2. 2026From Naive RAG to Deep Agentic Retrieval: An Evolving Context Engineering Pipeline for Regulatory Compliance
  3. 2026Citation-Closure Retrieval and Per-Rule Attribution for Real-World Regulatory Compliance Question Answering
  4. 2025RAGulating Compliance: A Multi-Agent Knowledge Graph for Regulatory QA
  5. 2026ARCCS: An Automated Regulatory Compliance Checking System
  6. 2025Explainable Compliance Detection with Multi-Hop Natural Language Inference on Assurance Case Structure
  7. 2026ComplianceNLP: Knowledge-Graph-Augmented RAG for Multi-Framework Regulatory Gap Detection
  8. 2026Navigating Global AI Regulation: A Multi-Jurisdictional Retrieval-Augmented Generation System