mlsanityData to 14 Oct 2026

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

arXiv 2604.10740 ↗First posted 12 Apr 2026cs.CLcited by 3

On the map: LLM agents and tool use → Agent threats, guardrails and governance

Abstract (arXiv)

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 .

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use. Builds on 34 of its 58 references that are in the map. First posted on arXiv 12 Apr 2026.

Builds on

34 of 58 references.

References · 34

  1. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  3. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
  4. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  5. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,784
  6. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,395
  7. 2021LexGLUE: A Benchmark Dataset for Legal Language Understanding in Englishcited by 310
  8. 2021CUAD: An Expert-Annotated NLP Dataset for Legal Contract Reviewcited by 236
  9. 2021ContractNLI: A Dataset for Document-level Natural Language Inference for Contractscited by 148
  10. 2020How Does NLP Benefit Legal System: A Summary of Legal Artificial Intelligencecited by 129
  11. 2023Large Language Models in Law: A Surveycited by 128
  12. 2023DISC-LawLLM: Fine-tuning Large Language Models for Intelligent Legal Servicescited by 120
22 more
  1. 2024Speculative RAG: Enhancing Retrieval Augmented Generation through Draftingcited by 77
  2. 2019Question Answering for Privacy Policies: Combining Computational and Legal Perspectivescited by 67
  3. 2023Large Language Models as Tax Attorneys: A Case Study in Legal Capabilities Emergencecited by 42
  4. 2023Legal Syllogism Prompting: Teaching Large Language Models for Legal Judgment Predictioncited by 38
  5. 2025LiCoMemory: Lightweight and Cognitive Agentic Memory for Efficient Long-Term Reasoningcited by 38
  6. 2022Uncoupled Learning Dynamics with O(log T) Swap Regret in Multiplayer Gamescited by 35
  7. 2023MAUD: An Expert-Annotated Legal NLP Dataset for Merger Agreement Understandingcited by 33
  8. 2025Think-While-Generating: On-the-Fly Reasoning for Personalized Long-Form Generationcited by 30
  9. 2022MUAD: Multiple Uncertainties for Autonomous Driving, a benchmark for multiple uncertainty types and taskscited by 24
  10. 2021Simple Uncoupled No-Regret Learning Dynamics for Extensive-Form Correlated Equilibriumcited by 22
  11. 2026Anatomy of Agentic Memory: Taxonomy and Empirical Analysis of Evaluation and System Limitationscited by 21
  12. 2022No-Regret Learning in Games with Noisy Feedback: Faster Rates and Adaptivity via Learning Rate Separationcited by 17
  13. 2025Semantic-Space Exploration and Exploitation in RLVR for LLM Reasoningcited by 17
  14. 2026FinCARDS: Card-Based Analyst Reranking for Financial Document Question Answeringcited by 16
  15. 2026Multimodal Multi-Agent Empowered Legal Judgment Predictioncited by 14
  16. 2025Learning to Substitute Words with Model-based Score Rankingcited by 10
  17. 2025CausalAbstain: Enhancing Multilingual LLMs with Causal Reasoning for Trustworthy Abstentioncited by 10
  18. 2026Stable-RAG: Mitigating Retrieval-Permutation-Induced Hallucinations in Retrieval-Augmented Generationcited by 5
  19. 2022Computing the optimal distributionally-robust strategy to commit tocited by 3
  20. 2026MultiPress: A Multi-Agent Framework for Interpretable Multimodal News Classificationcited by 2
  21. 2026EMSDialog: Synthetic Multi-person Emergency Medical Service Dialogue Generation from Electronic Patient Care Reports via Multi-LLM Agentscited by 2
  22. 2026Beyond the Individual: Virtualizing Multi-Disciplinary Reasoning for Clinical Intake via Collaborative Agentscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Learning to Control Summaries with Score Rankingcited by 4
  2. 2026Agent-GWO: Collaborative Agents for Dynamic Prompt Optimization in Large Language Modelscited by 0
  3. 2026Are LLMs Ready to Assist Physicians? PhysAssistBench for Interactive Doctor-Patient-EHR Assistancecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026A Stackelberg Framework for Resource-Aware LLM Agents: Learning, Repair, and Conditional Guarantees
  2. 2026Maat: Independent Deterministic Contract-Based Governance for Multi-Agent LLM Workflows
  3. 2026Reversa: A Reverse Documentation Engineering Framework for Converting Legacy Software into Operational Specifications for AI Agents
  4. 2024Agents on the Bench: Large Language Model Based Multi Agent Framework for Trustworthy Digital Justice
  5. 2026Evaluating Rational Contracting in Natural Language
  6. 2026Beyond Goodhart's Law: A Dynamic Benchmark for Evaluating Compliance in Multi-Agent Systems
  7. 2026Contract2Tool: Learning Preconditions and Effects for Reliable Tool-Augmented LLM Agents
  8. 2026A Policy Algebra for Trust-Preserving Agentic AI Execution