RCBSF: A Multi-Agent Framework for Automated Contract Revision via Stackelberg Game

TL;DR

RCBSF introduces a hierarchical multi-agent framework using a Stackelberg game to improve automated contract revision with risk constraints, achieving state-of-the-art results and better efficiency.

Contribution

The paper presents a novel bilevel Stackelberg game formulation for contract revision that guarantees convergence and improves performance over existing methods.

Findings

Achieves an average Risk Resolution Rate (RRR) of 84.21%.

Surpasses baseline methods in state-of-the-art performance.

Enhances token efficiency in contract revision tasks.

Abstract

Despite the widespread adoption of Large Language Models (LLMs) in Legal AI, their utility for automated contract revision remains impeded by hallucinated safety and a lack of rigorous behavioral constraints. To address these limitations, we propose the Risk-Constrained Bilevel Stackelberg Framework (RCBSF), which formulates revision as a non-cooperative Stackelberg game. RCBSF establishes a hierarchical Leader Follower structure where a Global Prescriptive Agent (GPA) imposes risk budgets upon a follower system constituted by a Constrained Revision Agent (CRA) and a Local Verification Agent (LVA) to iteratively optimize output. We provide theoretical guarantees that this bilevel formulation converges to an equilibrium yielding strictly superior utility over unguided configurations. Empirical validation on a unified benchmark demonstrates that RCBSF achieves state-of-the-art performance, surpassing iterative baselines with an average Risk Resolution Rate (RRR) of 84.21\% while enhancing token efficiency. Our code is available at https://github.com/xjiacs/RCBSF .