L-MARS: Legal Multi-Agent System with Agentic Search and Citation-Faithfulness Audit
Factual evidence
What the source reports
L-MARS is an open multi-agent legal QA system that uses agentic search and judge-driven evidence checks to audit citation faithfulness, addressing a common LLM failure in legal applications.
Inspect the evidence
- Inclusion basis
- Enterprise AI
- Publisher and source type
- arXiv cs.CL — Computation and Language · RESEARCH
- Published by source
- 9 November 2026
- Collected by OneBench
- 17 Jul 2026, 20:29 UK
Stored source excerpt
arXiv:2509.00761v4 Announce Type: replace-cross Abstract: Large language models are increasingly deployed for legal question answering, where evaluations typically focus on multiple-choice accuracy. This measure overlooks…
Short excerpt from the collected text, not the full source. Use the source link to read it in context.
The factual summary is a OneBench synthesis, not a quotation or independent verification. Collection time is not publication time. Open the source for its full context; related reporting can share the same underlying announcement.
OneBench interpretation
Institutional assessment
So what
Addressing citation faithfulness directly impacts regulatory compliance and model risk for any legal or policy application of LLMs, where accuracy is paramount.
Do what
Your legal, risk, and compliance teams will eventually demand similar evidence-checking capabilities for any LLM used in legal or regulatory contexts; current RAG architectures often fall short.