Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2604.12054 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908961489289216 |
|---|---|
| author | Ali, Mohammed Abdallah, Abdelrahman Jatowt, Adam |
| author_facet | Ali, Mohammed Abdallah, Abdelrahman Jatowt, Adam |
| contents | 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 |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_12054 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | REGREACT: Self-Correcting Multi-Agent Pipelines for Structured Regulatory Information Extraction Ali, Mohammed Abdallah, Abdelrahman Jatowt, Adam Multiagent Systems 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 |
| title | REGREACT: Self-Correcting Multi-Agent Pipelines for Structured Regulatory Information Extraction |
| topic | Multiagent Systems |
| url | https://arxiv.org/abs/2604.12054 |