{"ID":6497825,"CreatedAt":"2026-07-13T01:19:40.13847098Z","UpdatedAt":"2026-07-14T01:36:59.12045529Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.09099","arxiv_id":"2607.09099","title":"L-MAD: A Systematic Evaluation of Multi-Agent Debate Structures in Legal Reasoning","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.","short_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 structure...","url_abs":"https://arxiv.org/abs/2607.09099","url_pdf":"https://arxiv.org/pdf/2607.09099v1","authors":"[\"Tan-Minh Nguyen\",\"Hoang-Trung Nguyen\",\"Huu-Dong Nguyen\",\"Dinh-Truong Do\",\"Thi-Hai-Yen Vuong\",\"Le-Minh Nguyen\"]","published":"2026-07-10T05:08:02Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[]","has_code":false}