{"ID":2876197,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.00761","arxiv_id":"2509.00761","title":"L-MARS: Legal Multi-Agent Workflow with Orchestrated Reasoning and Agentic Search","abstract":"We present L-MARS (Legal Multi-Agent Workflow with Orchestrated Reasoning and Agentic Search), a multi-agent retrieval framework for grounded legal question answering that decomposes queries into structured sub-problems, retrieves evidence via agentic web search, filters results through a verification agent, and synthesizes cited answers. Existing legal QA benchmarks test either closed-book reasoning or retrieval over fixed corpora, but neither captures scenarios requiring current legal information. We introduce LegalSearchQA, a 50-question benchmark across five legal domains whose answers depend on recent developments that post-date model training data. L-MARS achieves 96.0% accuracy on LegalSearchQA, a 38.0% improvement over zero-shot performance (58.0%), while chain-of-thought prompting degrades performance to 30.0%. On Bar Exam QA (Zheng et al., 2025), a reasoning-focused benchmark of 594 bar examination questions, retrieval provides negligible gains (+0.7 percentage points), consistent with prior findings. These results show that agentic retrieval dramatically improves legal QA when tasks require up-to-date factual knowledge, but the benefit is benchmark-dependent, underscoring the need for retrieval-focused evaluation. Code and data are available at: https://github.com/boqiny/L-MARS","short_abstract":"We present L-MARS (Legal Multi-Agent Workflow with Orchestrated Reasoning and Agentic Search), a multi-agent retrieval framework for grounded legal question answering that decomposes queries into structured sub-problems, retrieves evidence via agentic web search, filters results through a verification agent, and synthe...","url_abs":"https://arxiv.org/abs/2509.00761","url_pdf":"https://arxiv.org/pdf/2509.00761v3","authors":"[\"Ziqi Wang\",\"Boqin Yuan\"]","published":"2025-08-31T09:23:26Z","proceeding":"cs.AI","tasks":"[\"cs.AI\",\"cs.CL\"]","methods":"[]","has_code":false,"code_links":[{"ID":610274,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2876197,"paper_url":"https://arxiv.org/abs/2509.00761","paper_title":"L-MARS: Legal Multi-Agent Workflow with Orchestrated Reasoning and Agentic Search","repo_url":"https://github.com/boqiny/L-MARS","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}