PAKTON: A Multi-Agent Framework for Question Answering in Long Legal Agreements
Raptopoulos, Petros, Filandrianos, Giorgos, Lymperaiou, Maria, Stamou, Giorgos
–arXiv.org Artificial Intelligence
Contract review is a complex and time-intensive task that typically demands specialized legal expertise, rendering it largely inaccessible to non-experts. Moreover, legal interpretation is rarely straightforward-ambiguity is pervasive, and judgments often hinge on subjective assessments. Compounding these challenges, contracts are usually confidential, restricting their use with proprietary models and necessitating reliance on open-source alternatives. To address these challenges, we introduce PAKTON: a fully open-source, end-to-end, multi-agent framework with plug-and-play capabilities. PAKTON is designed to handle the complexities of contract analysis through collaborative agent workflows and a novel retrieval-augmented generation (RAG) component, enabling automated legal document review that is more accessible, adaptable, and privacy-preserving. Experiments demonstrate that PAKTON outperforms both general-purpose and pretrained models in predictive accuracy, retrieval performance, explainability, completeness, and grounded justifications as evaluated through a human study and validated with automated metrics.
arXiv.org Artificial Intelligence
Sep-23-2025
- Country:
- Asia
- Myanmar > Tanintharyi Region
- Dawei (0.04)
- Singapore (0.04)
- Myanmar > Tanintharyi Region
- Europe
- Greece > Attica
- Athens (0.04)
- Middle East > Malta
- Eastern Region > Northern Harbour District > St. Julian's (0.04)
- Portugal (0.04)
- Greece > Attica
- North America
- Canada > Ontario
- Toronto (0.04)
- Dominican Republic (0.04)
- Mexico > Mexico City
- Mexico City (0.04)
- United States > Florida
- Miami-Dade County > Miami (0.04)
- Canada > Ontario
- Asia
- Genre:
- Research Report
- Experimental Study (0.67)
- New Finding (1.00)
- Research Report
- Industry:
- Information Technology > Security & Privacy (0.67)
- Law (1.00)
- Technology: