dorsal/arxiv
View SchemaLLM Agents in Law: Taxonomy, Applications, and Challenges
| Authors | Shuang Liu, Ruijia Zhang, Ruoyun Ma, Yujia Deng, Lanyi Zhu, Jiayu Li, Zelong Li, Zhibin Shen, Mengnan Du |
|---|---|
| Categories | |
| ArXiv ID | 2601.06216vv1 |
| URL | https://arxiv.org/abs/2601.06216 |
| License | http://arxiv.org/licenses/nonexclusive-distrib/1.0/ |
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in the legal domain, yet the deployment of standalone models faces significant limitations regarding hallucination, outdated information, and verifiability.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.
{
"annotation_id": "173b4021-0fb6-4b6c-989c-082d3033b9d8",
"date_created": "2026-02-17T05:53:07.511000Z",
"date_modified": "2026-02-17T05:53:07.511000Z",
"file_hash": "e073521dfeb29782d62beae868e84caa04060bb0f6f7471084b78c65441602fa",
"private": false,
"record": {
"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in the legal domain, yet the deployment of standalone models faces significant limitations regarding hallucination, outdated information, and verifiability.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.",
"arxiv_id": "2601.06216",
"authors": [
"Shuang Liu",
"Ruijia Zhang",
"Ruoyun Ma",
"Yujia Deng",
"Lanyi Zhu",
"Jiayu Li",
"Zelong Li",
"Zhibin Shen",
"Mengnan Du"
],
"categories": [
"cs.CY",
"cs.AI"
],
"license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
"title": "LLM Agents in Law: Taxonomy, Applications, and Challenges",
"url": "https://arxiv.org/abs/2601.06216",
"version": "v1"
},
"schema_id": "dorsal/arxiv",
"source": {
"execution_id": "57e28f16-ef03-4372-9c78-cacab537e439",
"id": "arXiv Dataset",
"type": "Model",
"variant": "snapshot-2026-01-17",
"version": "0.1.0"
},
"user_id": 1000002
}