LLM Agents in Law: Taxonomy, Applications, and Challenges
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909986474426368 |
|---|---|
| author | Liu, Shuang Zhang, Ruijia Ma, Ruoyun Deng, Yujia Zhu, Lanyi Li, Jiayu Li, Zelong Shen, Zhibin Du, Mengnan |
| author_facet | Liu, Shuang Zhang, Ruijia Ma, Ruoyun Deng, Yujia Zhu, Lanyi Li, Jiayu Li, Zelong Shen, Zhibin Du, Mengnan |
| contents | 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in the legal domain, yet the deployment of standalone models faces significant limitations regarding hallucination, outdated information, and verifiability.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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_06216 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | LLM Agents in Law: Taxonomy, Applications, and Challenges Liu, Shuang Zhang, Ruijia Ma, Ruoyun Deng, Yujia Zhu, Lanyi Li, Jiayu Li, Zelong Shen, Zhibin Du, Mengnan Computers and Society Artificial Intelligence 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in the legal domain, yet the deployment of standalone models faces significant limitations regarding hallucination, outdated information, and verifiability.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. |
| title | LLM Agents in Law: Taxonomy, Applications, and Challenges |
| topic | Computers and Society Artificial Intelligence |
| url | https://arxiv.org/abs/2601.06216 |