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

작성자

카테고리:

← 피드로
arXiv cs.AI · Tan-Minh Nguyen, Hoang-Trung Nguyen, Huu-Dong Nguyen, Dinh-Truong Do, Thi-Hai-Yen Vuong, Le-Minh Nguyen · 2026-07-13 AI

[Submitted on 10 Jul 2026]

View PDF HTML (experimental)

Abstract: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 \textit{over-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.

Submission history

From: Tan-Minh Nguyen [view email]
[v1] Fri, 10 Jul 2026 05:08:02 UTC (1,185 KB)

원문에서 계속 ↗

추출 본문 · 출처: arxiv.org · https://arxiv.org/abs/2607.09099

코멘트

답글 남기기

이메일 주소는 공개되지 않습니다. 필수 필드는 *로 표시됩니다