LLM Agents in Law: Taxonomy, Applications, and Challenges
This is an incremental survey paper that addresses the problem of improving legal AI systems for practitioners and researchers by summarizing existing work on LLM agents in law.
The paper tackles the limitations of standalone large language models in law, such as hallucination and outdated information, by surveying LLM agents as a solution, analyzing their transition, taxonomy, evaluation, and challenges for legal tasks.
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in the legal domain, yet the deployment of standalone models faces significant limitations regarding hallucination, outdated information, and verifiability.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.