mlsanityData to 14 Oct 2026

Multi-Agent Simulator Drives Language Models for Legal Intensive Interaction

arXiv 2502.06882 ↗First posted 8 Feb 2025cs.CL cs.AIcited by 22

On the map: LLM agents and tool use → Social simulation and multi-agent debate

Abstract (arXiv)

Large Language Models (LLMs) have significantly advanced legal intelligence, but the scarcity of scenario data impedes the progress toward interactive legal scenarios. This paper introduces a Multi-agent Legal Simulation Driver (MASER) to scalably generate synthetic data by simulating interactive legal scenarios. Leveraging real-legal case sources, MASER ensures the consistency of legal attributes between participants and introduces a supervisory mechanism to align participants' characters and behaviors as well as addressing distractions. A Multi-stage Interactive Legal Evaluation (MILE) benchmark is further constructed to evaluate LLMs' performance in dynamic legal scenarios. Extensive experiments confirm the effectiveness of our framework.

Key facts. Cited by 22 papers in the map (data through 14 Oct 2026). Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use. Builds on 22 of its 41 references that are in the map. First posted on arXiv 8 Feb 2025.

Builds on

22 of 41 references.

Closest ancestors · 4

Same direction, newest first

  1. 2024Identity-Driven Hierarchical Role-Playing Agents28 Jul
  2. 2024Can Large Language Model Agents Simulate Human Trust Behavior?7 Feb
  3. 2023Character-LLM: A Trainable Agent for Role-Playing16 Oct
  4. 2023Generative Agents: Interactive Simulacra of Human Behavior7 Apr

Other references · 18

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2024The Llama 3 Herd of Modelscited by 14,715
  3. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  4. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
  5. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,224
  6. 2024Qwen2 Technical Reportcited by 2,120
  7. 2023Baichuan 2: Open Large-scale Language Modelscited by 670
  8. 2023Large Language Model as Attributed Training Data Generator: A Tale of Diversity and Biascited by 232
  9. 2024Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalizationcited by 208
  10. 2023DISC-LawLLM: Fine-tuning Large Language Models for Intelligent Legal Servicescited by 120
  11. 2024AgentSense: Benchmarking Social Intelligence of Language Agents through Interactive Scenarioscited by 40
  12. 2018LexNLP: Natural language processing and information extraction for legal and regulatory textscited by 28
6 more
  1. 2024Synergistic Multi-Agent Framework with Trajectory Learning for Knowledge-Intensive Taskscited by 23
  2. 2021Learning Fine-grained Fact-Article Correspondence in Legal Casescited by 15
  3. 2021Dependency Learning for Legal Judgment Prediction with a Unified Text-to-Text Transformercited by 13
  4. 2024BEYOND DIALOGUE: A Profile-Dialogue Alignment Framework Towards General Role-Playing Language Modelcited by 13
  5. 2024Fine-Tuned Large Language Model for Visualization System: A Study on Self-Regulated Learning in Educationcited by 12
  6. 2024Human vs. LMMs: Exploring the Discrepancy in Emoji Interpretation and Usage in Digital Communicationcited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 9; 2026: 13.

22 papers.

Sort:

By area:

  1. 2025FaithCoT-Bench: Benchmarking Instance-Level Faithfulness of Chain-of-Thought Reasoningcited by 26
  2. 2025A Survey on Agent Workflow -- Status and Futurecited by 14
  3. 2025Ready Jurist One: Benchmarking Language Agents for Legal Intelligence in Dynamic Environmentscited by 13
  4. 2025FinTeam: A Multi-Agent Collaborative Intelligence System for Comprehensive Financial Scenarioscited by 5
  5. 2026LLM Agents in Law: Taxonomy, Applications, and Challengescited by 5
  6. 2026Data Science and Technology Towards AGI Part I: Tiered Data Managementcited by 4
  7. 2026Human Values Matter: Investigating How Misalignment Shapes Collective Behaviors in LLM Agent Communitiescited by 4
  8. 2025Law in Silico: Simulating Legal Society with LLM-Based Agentscited by 3
  9. 2025PAKTON: A Multi-Agent Framework for Question Answering in Long Legal Agreementscited by 1
  10. 2026LinguaGame: A Linguistically Grounded Game-Theoretic Paradigm for Multi-Agent Dialogue Generationcited by 1
  11. 2026PsyCLIENT: Client Simulation via Conversational Trajectory Modeling for Trainee Practice and Model Evaluation in Mental Health Counselingcited by 1
  12. 2026When to Call an Apple Red: Humans Follow Introspective Rules, VLMs Don'tcited by 1
10 more
  1. 2026CyberJurors: A Multi-Agent Simulation Task for E-Commerce Disputes Verdictcited by 1
  2. 2025PL-CA: A Parametric Legal Case Augmentation Frameworkcited by 0
  3. 2025EduDial: Constructing a Large-scale Multi-turn Teacher-Student Dialogue Corpuscited by 0
  4. 2025PyFi: Toward Pyramid-like Financial Image Understanding for VLMs via Adversarial Agentscited by 0
  5. 2026DLawBench: Evaluating LLMs Through Multi-Turn Legal Consultationcited by 0
  6. 2026CatalogAgent: A Supervisor-mediated Self-Learning System Enabling Context Engineering for GenAI Modelscited by 0
  7. 2026LiveSim: Simulating Environment-Shaped Users in Multi-Agent Live-Stream Ecosystemscited by 0
  8. 2026When Does Defendant Statement Matter? A Study of Bias and Persuasion in LLM-Simulated Jurorscited by 0
  9. 2026ParaAgent: Reinforcing Parallel Acting in Open-World Tool Environmentscited by 0
  10. 2026LawCompass: Navigating from Legal QA to Multi-Agent Deep Research with Grounded Evidencecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025MASLegalBench: Benchmarking Multi-Agent Systems in Deductive Legal Reasoning
  2. 2025Chinese Court Simulation with LLM-Based Agent System
  3. 2024Can Large Language Models Grasp Legal Theories? Enhance Legal Reasoning with Insights from Multi-Agent Collaboration
  4. 2026Investigating Multi-Agent Deliberation in Law
  5. 2024LegalAgentBench: Evaluating LLM Agents in Legal Domain
  6. 2025Mitigating Manipulation and Enhancing Persuasion: A Reflective Multi-Agent Approach for Legal Argument Generation
  7. 2026Evaluation of Large Language Models in Legal Applications: Challenges, Methods, and Future Directions
  8. 2026Ordinary, Reasonable Chatbots: Do AI Models Track Human Legal Judgments?