Ready Jurist One: Benchmarking Language Agents for Legal Intelligence in Dynamic Environments

TL;DR

This paper introduces a new interactive legal environment and evaluation framework to assess language models' legal reasoning and procedural skills in dynamic, real-world scenarios, revealing current models' limitations.

Contribution

It presents J1-ENVS and J1-EVAL, pioneering tools for benchmarking legal AI in dynamic environments, highlighting gaps in models' procedural capabilities.

Findings

Models perform well in legal knowledge but poorly in procedural tasks.

GPT-4o achieves less than 60% overall performance.

Dynamic legal intelligence remains a significant challenge.

Abstract

The gap between static benchmarks and the dynamic nature of real-world legal practice poses a key barrier to advancing legal intelligence. To this end, we introduce J1-ENVS, the first interactive and dynamic legal environment tailored for LLM-based agents. Guided by legal experts, it comprises six representative scenarios from Chinese legal practices across three levels of environmental complexity. We further introduce J1-EVAL, a fine-grained evaluation framework, designed to assess both task performance and procedural compliance across varying levels of legal proficiency. Extensive experiments on 17 LLM agents reveal that, while many models demonstrate solid legal knowledge, they struggle with procedural execution in dynamic settings. Even the SOTA model, GPT-4o, falls short of 60% overall performance. These findings highlight persistent challenges in achieving dynamic legal intelligence and offer valuable insights to guide future research.