用博弈论框架自动修订合同，提升安全性和效率
RCBSF: A Multi-Agent Framework for Automated Contract Revision via Stackelberg Game
- 设计双层博弈结构，由主控代理设定风险预算
- 在统一基准上实现84.21%的风险解决率，优于现有方法
- 适合法律AI、自动化合同系统研发人员使用
尽管大型语言模型在法律人工智能中广泛应用，但其在自动合同修订中的应用仍受限于幻觉安全问题和缺乏严格的约束机制。为此，我们提出风险约束双层斯塔克尔伯格框架（RCBSF），将修订过程建模为非合作斯塔克尔伯格博弈。该框架构建了主从层级结构：全局规范代理（GPA）向由受限修订代理（CRA）和局部验证代理（LVA）组成的从属系统施加风险预算，以迭代优化输出。我们提供了理论保证，证明该双层结构能收敛至均衡状态，且收益显著优于无引导配置。在统一基准上的实证验证表明，RCBSF达到领先性能，平均风险解决率（RRR）为84.21%，同时提升了词元效率。代码已开源：https://github.com/xjiacs/RCBSF。
原文摘要 · Abstract (English)
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 .
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。