LLM Agents in Law: Taxonomy, Applications, and Challenges

TL;DR

This paper surveys the development and application of large language model agents in the legal domain, highlighting their capabilities, challenges, and future research directions.

Contribution

It provides a structured taxonomy, analyzes technical transitions, discusses evaluation methods, and identifies open challenges for legal LLM agents.

Findings

Legal LLM agents improve task performance with planning and tool use.

Current applications span multiple legal practice areas.

Open challenges include robustness and autonomous decision-making.

Abstract

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in the legal domain, yet the deployment of standalone models faces significant limitations regarding hallucination, outdated information, and verifiability.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.