mlsanityData to 7 Oct 2026

L-MAD: A Systematic Evaluation of Multi-Agent Debate Structures in Legal Reasoning

arXiv 2607.09099 ↗First posted 10 Jul 2026cs.AIcited by 0

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

Abstract (arXiv)

While multi-agent debate (MAD) frameworks have shown significant potential in general reasoning, their effectiveness in highly structured, knowledge-heavy legal domains remains under-explored. In this work, we introduce the Legal Multi-Agent Debate (L-MAD) framework to systematically evaluate different debate structures and aggregation methods within Legal Textual Entailment. By assigning distinct expert personas to multiple agents, L-MAD improves upon strong single-agent baselines by up to 8%. Furthermore, analyzing how debate scales reveals a clear trade-off: increasing the agent population reduces inconsistency and improves accuracy, whereas extending discussion rounds induces a detrimental textitover-deliberation drift where agents reinforce each other's mistakes. Ultimately, our findings outline the practical boundaries and safety margins of deploying collaborative multi-agent systems in high-stakes legal reasoning environments.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use. Builds on 21 of its 31 references that are in the map. First posted on arXiv 10 Jul 2026.

Builds on

21 of 31 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025MALLM: Multi-Agent Large Language Models Framework15 Sep
  2. 2025Debate or Vote: Which Yields Better Decisions in Multi-Agent Large Language Models?24 Aug
  3. 2025Voting or Consensus? Decision-Making in Multi-Agent Debate26 Feb

Other references · 18

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2024The Llama 3 Herd of Modelscited by 14,192
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  4. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  5. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
  6. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,739
  7. 2023Large Language Models Cannot Self-Correct Reasoning Yetcited by 965
  8. 2019Adversarial NLI: A New Benchmark for Natural Language Understandingcited by 798
  9. 2022Complexity-Based Prompting for Multi-Step Reasoningcited by 387
  10. 2021LexGLUE: A Benchmark Dataset for Legal Language Understanding in Englishcited by 302
  11. 2020How Does NLP Benefit Legal System: A Summary of Legal Artificial Intelligencecited by 128
  12. 2021Lawformer: A Pre-trained Language Model for Chinese Legal Long Documentscited by 115
6 more
  1. 2023Exchange-of-Thought: Enhancing Large Language Model Capabilities through Cross-Model Communicationcited by 78
  2. 2022Legal Prompting: Teaching a Language Model to Think Like a Lawyercited by 60
  3. 2025LEXam: Benchmarking Legal Reasoning on 340 Law Examscited by 52
  4. 2024LLM Voting: Human Choices and AI Collective Decision Makingcited by 47
  5. 2024Persona is a Double-edged Sword: Mitigating the Negative Impact of Role-playing Prompts in Zero-shot Reasoning Taskscited by 28
  6. 2024Multi-Agent Large Language Models for Conversational Task-Solvingcited by 24

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Investigating Multi-Agent Deliberation in Law
  2. 2025Can LLM Agents Really Debate? A Controlled Study of Multi-Agent Debate in Logical Reasoning
  3. 2023Should we be going MAD? A Look at Multi-Agent Debate Strategies for LLMs
  4. 2025Debate-Feedback: A Multi-Agent Framework for Efficient Legal Judgment Prediction
  5. 2026AgenticSimLaw: A Juvenile Courtroom Multi-Agent Debate Simulation for Explainable High-Stakes Tabular Decision Making
  6. 2025L-MARS: Legal Multi-Agent System with Agentic Search and Citation-Faithfulness Audit
  7. 2026Courtroom-Style Multi-Agent Debate with Progressive RAG and Role-Switching for Controversial Claim Verification
  8. 2026Tool-MAD: A Multi-Agent Debate Framework for Fact Verification with Diverse Tool Augmentation and Adaptive Retrieval