Ready Jurist One: Benchmarking Language Agents for Legal Intelligence in Dynamic Environments
This addresses the gap between static benchmarks and real-world legal practice for researchers and developers in legal AI, though it is incremental as it focuses on benchmarking rather than novel methods.
The paper tackles the problem of evaluating language agents in dynamic legal environments by introducing J1-ENVS, an interactive benchmark with scenarios from Chinese legal practice, and finds that even state-of-the-art models like GPT-4o achieve less than 60% overall performance, struggling with procedural execution.
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.