L-MARS: Legal Multi-Agent System with Agentic Search and Citation-Faithfulness Audit
cs.AI, cs.CL
Submitted: 2025-08-31
Updated: 2026-11-05
Terminology
Sources
- OpenAI GPT-5 System Card
- LEGAL-BERT: The Muppets straight out of Law School
- Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLP
- AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation
- Search-o1: Agentic Search-Enhanced Large Reasoning Models
- WebThinker: Empowering Large Reasoning Models with Deep Research Capability
- OpenAI o1 System Card
- Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
- Self-Consistency Improves Chain of Thought Reasoning in Language Models
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Pile of Law: Learning Responsible Data Filtering from the Law and a 256GB Open-Source Legal Dataset
- LegalBench: A Collaboratively Built Benchmark for Measuring Legal Reasoning in Large Language Models
- Case law retrieval: problems, methods, challenges and evaluations in the last 20 years
- Hallucination is Inevitable: An Innate Limitation of Large Language Models
- LEXam: Benchmarking Legal Reasoning on 340 Law Exams
- ReAct: Synergizing Reasoning and Acting in Language Models
- Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG
- Language Models (Mostly) Know What They Know
- Reflexion: Language Agents with Verbal Reinforcement Learning
- LawBench: Benchmarking Legal Knowledge of Large Language Models
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents