Metraipolis › archive › dc_67dcec8d82c0
LegalEvolver: Agentic Legal Judgment Prediction via Rubric-Guided Self-Evolution — arXiv:2611.06381
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.06381
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-05T18:17:01.761Z
- SHA-256 of the archived text
d35bd38e873a187304ebe97aecd97ab512628d7ddad593c76b0f7bbe60b5fd85- Stable URL of this page
https://metraipolis.com/documento/dc_67dcec8d82c0
How to cite
LegalEvolver: Agentic Legal Judgment Prediction via Rubric-Guided Self-Evolution — arXiv:2611.06381 — arXiv (en), https://arxiv.org/abs/2611.06381 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_67dcec8d82c0 (Metraipolis archive dc_67dcec8d82c0, sha256 d35bd38e873a187304ebe97aecd97ab512628d7ddad593c76b0f7bbe60b5fd85)
BibTeX
@misc{dc67dcec8d82c0,
title = {LegalEvolver: Agentic Legal Judgment Prediction via Rubric-Guided Self-Evolution — arXiv:2611.06381},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.06381},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_67dcec8d82c0; sha256 d35bd38e873a187304ebe97aecd97ab512628d7ddad593c76b0f7bbe60b5fd85},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.06381. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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.
Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2611.06381 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-05T18:12:49.010Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).