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

TL;DR

RegReAct is a multi-agent framework for extracting structured regulatory information that self-corrects errors through iterative validation, improving accuracy over single-pass models.

Contribution

It introduces a self-correcting multi-stage pipeline with an Observe--Diagnose--Repair loop for hierarchical and dependency-aware regulatory information extraction.

Findings

Outperforms GPT-4o baseline in structural and semantic metrics

Constructs a typed criterion graph for structural accuracy

Resolves external dependencies by retrieving and embedding legal content

Abstract

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 \textsc{RegReAct}, a self-correcting multi-agent framework that decomposes regulatory information extraction into seven specialized stages, each with an \textit{Observe--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, \textsc{RegReAct} 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 \textsc{RegReAct} 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 \textsc{RegReAct} outperforms it across all structural and semantic metrics. Code and data will be made publicly available: https://github.com/RECOR-Benchmark/RECOR