# LegalEvolver: Agentic Legal Judgment Prediction via Rubric-Guided Self-Evolution

DevFeed: [LegalEvolver: Agentic Legal Judgment Prediction via Rubric-Guided Self-Evolution](<https://devfeed.tech/articles/legalevolver-agentic-legal-judgment-prediction-via-rubric-guided-self-evolution-118459.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.06381>)

Author: Xinyu Yang, Jiejun Tan, Chenlong Deng, Chenghao Zhang, Tongyu Wen, Zhicheng Dou

Published: 2026-11-05T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [Enhancing AI model performance](<https://devfeed.tech/topics/enhancing-ai-model-performance.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [agents](<https://devfeed.tech/tags/agents.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [comparisons](<https://devfeed.tech/tags/comparisons.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cl](<https://devfeed.tech/tags/cs-cl.md>), [domain](<https://devfeed.tech/tags/domain.md>), [effectiveness](<https://devfeed.tech/tags/effectiveness.md>), [efficiency](<https://devfeed.tech/tags/efficiency.md>), [evolution](<https://devfeed.tech/tags/evolution.md>), [experience](<https://devfeed.tech/tags/experience.md>), [external](<https://devfeed.tech/tags/external.md>), [fixed](<https://devfeed.tech/tags/fixed.md>), [framework](<https://devfeed.tech/tags/framework.md>), [generate](<https://devfeed.tech/tags/generate.md>), [generation](<https://devfeed.tech/tags/generation.md>), [guidance](<https://devfeed.tech/tags/guidance.md>), [issue](<https://devfeed.tech/tags/issue.md>), [legal](<https://devfeed.tech/tags/legal.md>), [llm](<https://devfeed.tech/tags/llm.md>), [prediction](<https://devfeed.tech/tags/prediction.md>)

## AI overview

LegalEvolver improves legal judgment prediction retrieval by optimizing queries to surface latent legal issues and legally salient details that direct queries from the initial request may miss. It uses heuristically optimized queries to seed more efficient search-trajectory generation, then summarizes rollout experience into rubrics that guide iterative rubric optimization and reinforcement learning. The abstract reports that query optimization improves end-to-end performance on benchmarks, rubric guidance outperforms direct supervised fine-tuning followed by RL, and evolving rubrics outperform fixed rubrics. It provides no benchmark names or quantitative results.

## Source excerpt

arXiv:2611.06381v1 Announce Type: new Abstract: As LLM-based agents develop, they have been increasingly applied in the legal domain. Legal Judgment Prediction~(LJP) requires models to conduct multi-step reasoning and external legal evidence retrieval. Existing legal search agents' performance is often constrained by the quality of retrieval queries. They often formulate queries directly from the initial user request, overlooking latent legal issues and legally salient details. To address this issue, we propose \emph{LegalEvolver}, a query optimization framework specifically designed to generate legally informative queries for LJP-oriented retrieval. Sampling high-quality optimized queries and their corresponding search trajectories is challenging, as relying solely on unguided high-temperature rollouts is both inefficient and constrained by the model's initial capabilities. We therefore heuristically optimize queries as seeds, improving the efficiency of trajectory generation. Furthermore, we summarize rollout experience into rubrics and use them to guide multi-round iterative self-evolution. Iteratively performing rubric optimization and rubric-guided RL enables the model to surpass its initial performance ceiling. End-to-end performance on extensive benchmarks demonstrates the effectiveness of query optimization on LJP. Comparisons with direct SFT followed by RL demonstrate the effectiveness of rubric guidance. Evolving rubrics further outperform fixed rubrics, confirming the benefits of self-evolution.