mlsanityData to 14 Oct 2026

LLM Agents in Law: Taxonomy, Applications, and Challenges

arXiv 2601.06216 ↗First posted 8 Jan 2026cs.CY cs.AIcited by 5

On the map: LLM agents and tool use → Social simulation and multi-agent debate

Abstract (arXiv)

Large language models (LLMs) have precipitated a dramatic improvement in the legal domain, yet the deployment of standalone models faces significant limitations regarding hallucination, outdated information, and verifiability. Recently, LLM agents have attracted significant attention as a solution to these challenges, utilizing advanced capabilities such as planning, memory, and tool usage to meet the rigorous standards of legal practice. In this paper, we present a comprehensive survey of LLM agents for legal tasks, analyzing how these architectures bridge the gap between technical capabilities and domain-specific needs. Our major contributions include: (1) systematically analyzing the technical transition from standard legal LLMs to legal agents; (2) presenting a structured taxonomy of current agent applications across distinct legal practice areas; (3) discussing evaluation methodologies specifically for agentic performance in law; and (4) identifying open challenges and outlining future directions for developing robust and autonomous legal assistants.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use. Builds on 80 of its 147 references that are in the map. First posted on arXiv 8 Jan 2026.

Builds on

80 of 147 references.

Closest ancestors · 26

Same direction, newest first

  1. 2025Building from Scratch: A Multi-Agent Framework with Human-in-the-Loop for Multilingual Legal Terminology Mapping15 Dec
  2. 2025Towards Trustworthy Legal AI through LLM Agents and Formal Reasoning26 Nov
  3. 2025Law in Silico: Simulating Legal Society with LLM-Based Agents28 Oct
  4. 2025Deterministic Legal Agents: A Canonical Primitive API for Auditable Reasoning over Temporal Knowledge Graphs7 Oct
  5. 2025LegalSim: Multi-Agent Simulation of Legal Systems for Discovering Procedural Exploits3 Oct
  6. 2025MASLegalBench: Benchmarking Multi-Agent Systems in Deductive Legal Reasoning29 Sep
  7. 2025Simulating Dispute Mediation with LLM-Based Agents for Legal Research8 Sep
  8. 2025SAMVAD: A Multi-Agent System for Simulating Judicial Deliberation Dynamics in India4 Sep
  9. 2025LLM-empowered Agents Simulation Framework for Scenario Generation in Service Ecosystem Governance1 Sep
  10. 2025L-MARS: Legal Multi-Agent System with Agentic Search and Citation-Faithfulness Audit31 Aug
  11. 2025Chinese Court Simulation with LLM-Based Agent System24 Aug
  12. 2025Ready Jurist One: Benchmarking Language Agents for Legal Intelligence in Dynamic Environments5 Jul
14 more
  1. 2025Mitigating Manipulation and Enhancing Persuasion: A Reflective Multi-Agent Approach for Legal Argument Generation3 Jun
  2. 2025Debate-Feedback: A Multi-Agent Framework for Efficient Legal Judgment Prediction7 Apr
  3. 2025Multi-Agent Simulator Drives Language Models for Legal Intensive Interaction8 Feb
  4. 2024LegalAgentBench: Evaluating LLM Agents in Legal Domain23 Dec
  5. 2024LAW: Legal Agentic Workflows for Custody and Fund Services Contracts15 Dec
  6. 2024Political Actor Agent: Simulating Legislative System for Roll Call Votes Prediction with Large Language Models10 Dec
  7. 2024Can Large Language Models Grasp Legal Theories? Enhance Legal Reasoning with Insights from Multi-Agent Collaboration3 Oct
  8. 2024Safeguarding Decentralized Social Media: LLM Agents for Automating Community Rule Compliance13 Sep
  9. 2024AgentCourt: Simulating Court with Adversarial Evolvable Lawyer Agents15 Aug
  10. 2024LawLuo: A Multi-Agent Collaborative Framework for Multi-Round Chinese Legal Consultation23 Jul
  11. 2024Simulating The U.S. Senate: An LLM-Driven Agent Approach to Modeling Legislative Behavior and Bipartisanship26 Jun
  12. 2024Cooperate or Collapse: Emergence of Sustainable Cooperation in a Society of LLM Agents25 Apr
  13. 2024AgentsCourt: Building Judicial Decision-Making Agents with Court Debate Simulation and Legal Knowledge Augmentation5 Mar
  14. 2023Chatlaw: A Multi-Agent Legal Assistant based on a Role-Aligned Mixture-of-Experts Architecture28 Jun

Other references · 54

  1. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  2. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  3. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,601
  4. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,439
  5. 2020Knowledge Graphscited by 621
  6. 2023LegalBench: A Collaboratively Built Benchmark for Measuring Legal Reasoning in Large Language Modelscited by 336
  7. 2023FreshLLMs: Refreshing Large Language Models with Search Engine Augmentationcited by 318
  8. 2024Hallucination-Free? Assessing the Reliability of Leading AI Legal Research Toolscited by 176
  9. 2024Large Legal Fictions: Profiling Legal Hallucinations in Large Language Modelscited by 150
  10. 2023Large Language Models in Law: A Surveycited by 128
  11. 2023LawBench: Benchmarking Legal Knowledge of Large Language Modelscited by 117
  12. 2024FinCon: A Synthesized LLM Multi-Agent System with Conceptual Verbal Reinforcement for Enhanced Financial Decision Makingcited by 113
38 more
  1. 2024A Survey on Large Language Models for Critical Societal Domains: Finance, Healthcare, and Lawcited by 74
  2. 2024(A)I Am Not a Lawyer, But...: Engaging Legal Experts towards Responsible LLM Policies for Legal Advicecited by 63
  3. 2024LawLLM: Law Large Language Model for the US Legal Systemcited by 37
  4. 2024LexEval: A Comprehensive Chinese Legal Benchmark for Evaluating Large Language Modelscited by 37
  5. 2023Interpretable Long-Form Legal Question Answering with Retrieval-Augmented Large Language Modelscited by 35
  6. 2024Constructing Domain-Specific Evaluation Sets for LLM-as-a-judgecited by 30
  7. 2023A Comprehensive Evaluation of Large Language Models on Legal Judgment Predictioncited by 28
  8. 2025A Survey on Responsible LLMs: Inherent Risk, Malicious Use, and Mitigation Strategycited by 20
  9. 2025On Verifiable Legal Reasoning: A Multi-Agent Framework with Formalized Knowledge Representationscited by 18
  10. 2024AutoPatent: A Multi-Agent Framework for Automatic Patent Generationcited by 16
  11. 2024CitaLaw: Enhancing LLM with Citations in Legal Domaincited by 16
  12. 2025SafeScientist: Toward Risk-Aware Scientific Discoveries by LLM Agentscited by 16
  13. 2025Is Your LLM-Based Multi-Agent a Reliable Real-World Planner? Exploring Fraud Detection in Travel Planningcited by 15
  14. 2025Enhancing LLM-Based Agents via Global Planning and Hierarchical Executioncited by 13
  15. 2024Evaluating AI for Law: Bridging the Gap with Open-Source Solutionscited by 11
  16. 2025Large Language Models Meet Legal Artificial Intelligence: A Surveycited by 10
  17. 2024Evaluation Ethics of LLMs in Legal Domaincited by 9
  18. 2025Debate-Driven Multi-Agent LLMs for Phishing Email Detectioncited by 9
  19. 2025ContractEval: Benchmarking LLMs for Clause-Level Legal Risk Identification in Commercial Contractscited by 9
  20. 2025AI Agent Governance: A Field Guidecited by 8
  21. 2025TRIDENT: Benchmarking LLM Safety in Finance, Medicine, and Lawcited by 8
  22. 2025RAGulating Compliance: A Multi-Agent Knowledge Graph for Regulatory QAcited by 6
  23. 2025An LLM Agentic Approach for Legal-Critical Software: A Case Study for Tax Prep Softwarecited by 6
  24. 2025Agent4FaceForgery: Multi-Agent LLM Framework for Realistic Face Forgery Detectioncited by 5
  25. 2025Compliance Brain Assistant: Conversational Agentic AI for Assisting Compliance Tasks in Enterprise Environmentscited by 4
  26. 2025Co-Investigator AI: The Rise of Agentic AI for Smarter, Trustworthy AML Compliance Narrativescited by 4
  27. 2024Towards Automated Patent Workflows: AI-Orchestrated Multi-Agent Framework for Intellectual Property Management and Analysiscited by 3
  28. 2025LegalEval-Q: A New Benchmark for The Quality Evaluation of LLM-Generated Legal Textcited by 3
  29. 2025PhishDebate: An LLM-Based Multi-Agent Framework for Phishing Website Detectioncited by 3
  30. 2025MASCA: LLM based-Multi Agents System for Credit Assessmentcited by 3
  31. 2025AutoSpec: An Agentic Framework for Automatically Drafting Patent Specificationcited by 3
  32. 2025NegotiationGym: Self-Optimizing Agents in a Multi-Agent Social Simulation Environmentcited by 3
  33. 2025Enforcing Cybersecurity Constraints for LLM-driven Robot Agents for Online Transactionscited by 2
  34. 2025LLM-Based Agents for Competitive Landscape Mapping in Drug Asset Due Diligencecited by 2
  35. 2025PAKTON: A Multi-Agent Framework for Question Answering in Long Legal Agreementscited by 1
  36. 2025Privacy Artifact ConnecTor (PACT): Embedding Enterprise Artifacts for Compliance AI Agentscited by 1
  37. 2025Retrieval-Augmented Multi-Agent System for Rapid Statement of Work Generationcited by 1
  38. 2025JustEva: A Toolkit to Evaluate LLM Fairness in Legal Knowledge Inferencecited by 1

50 most cited of 54 All 54 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 5.

5 papers.

  1. 2026Adaptive Collaboration of Arena-Based Argumentative LLMs for Explainable and Contestable Legal Reasoningcited by 4
  2. 2026HARVE: Hacking-Aware Reward-Head Vector Editing for Robust Reward Modelscited by 2
  3. 2026Collective Opinion Dynamics in Structured LLM Populationscited by 0
  4. 2026Natural-Language Workflows Are Not Software Yet: Artifact-Driven Compilation for Reliable Agent Executioncited by 0
  5. 2026JusticeAxis: Benchmarking Legal Judgment between Rigid Rule Application and Ungrounded Discretioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Evaluation of Large Language Models in Legal Applications: Challenges, Methods, and Future Directions
  2. 2025EU-Agent-Bench: Measuring Illegal Behavior of LLM Agents Under EU Law
  3. 2025When AIs Judge AIs: The Rise of Agent-as-a-Judge Evaluation for LLMs
  4. 2023Large Language Models as Tax Attorneys: A Case Study in Legal Capabilities Emergence
  5. 2025When Large Language Models Meet Law: Dual-Lens Taxonomy, Technical Advances, and Ethical Governance
  6. 2026Can LLMs Time Travel? Enhancing Temporal Consistency in Legal Agentic Search through Reinforcement Learning
  7. 2026Investigating Multi-Agent Deliberation in Law
  8. 2025LeMAJ (Legal LLM-as-a-Judge): Bridging Legal Reasoning and LLM Evaluation