arXiv AI
Test-Time Agent Evolution for Long-Horizon Legal Reasoning
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
Hugging Face Trending Papers
Jun 17
LegalWorld: A Life-Cycle Interactive Environment for Legal Agents
Civil litigation is inherently a life-cycle process: what a lawyer drafts on day one constrains what unfolds at trial months later. Yet existing legal benchmarks evaluate isolated subtasks, and prior legal-agent simulators reinitialize each scenario from shared ground truth, leaving cross-stage causal dependencies unmodeled.
Hugging Face Trending Papers
Jun 3
Parthenon Law: A Self-Evolving Legal-Agent Framework
As agents grow more capable, legal-domain LLM agents promise to turn document-heavy matters into reviewable work products -- yet reliable deployment faces three obstacles: no large-scale evidence on how today's strongest model-and-harness combinations behave on end-to-end legal matters; no agent architecture adapted to the legal vertical, only general-purpose harnesses; and, in a setting that keeps shifting with new facts, authorities, and deadlines, no mechanism for systems to learn from their own outcomes. We address each.
arXiv AI
Jun 4
Parthenon Law: A Self-Evolving Legal-Agent Framework
arXiv:2606. 04602v1 Announce Type: new Abstract: As agents grow more capable, legal-domain LLM agents promise to turn document-heavy matters into reviewable work products -- yet reliable deployment faces three obstacles: no large-scale evidence on how today's strongest model-and-harness combinations behave on end-to-end legal matters; no agent architecture adapted to the legal vertical, only general-purpose harnesses; and, in a setting that keeps shifting with new facts, authorities, and deadlines, no mechanism for systems to learn from their own outcomes.
arXiv AI
Aug 18
When Do LLMs Apply the Wrong Law? Diagnosing LLM Failures in Temporal Legal Reasoning
arXiv:2608. 14610v1 Announce Type: new Abstract: Legal reasoning tasks such as legal judgment prediction (LJP) require identifying the temporally correct version of the law governing a case -- a capability we term temporal applicable-law determination.
arXiv Computation and Language
Sep 24
LEGO: Synergizing Expert GraphRAG and Expert Chain-of-Thought for Legal Reasoning
LEGO is a dual‑module framework that combines a Legal Expert GraphRAG system with an expert Chain‑of‑Thought approach to enhance complex legal reasoning. The GraphRAG component uses an expert‑annotated civil code graph and a greedy normative‑coverage retrieval algorithm to extract relevant provision subgraphs, while the Chain‑of‑Thought module structures retrieved provisions and case facts into a Provision‑Fact‑Conclusion reasoning flow. Using a Qwen3‑8B backbone, LEGO achieves 40.53% exact‑match accuracy on LawExamQA_Civil, surpassing baseline RAG and CoT models and matching larger models on multi‑hop and open‑ended benchmarks, with ablation studies confirming the complementary benefits of both modules.
arXiv AI
1d ago
LegalEvolver: Agentic Legal Judgment Prediction via Rubric-Guided Self-Evolution
LegalEvolver is a query‑optimization framework for legal judgment prediction that generates legally informative queries to improve retrieval quality. It uses heuristic query seeding, summarizes rollout experiences into rubrics, and applies rubric‑guided reinforcement learning for iterative self‑evolution. Experiments on large benchmarks show that evolving rubrics outperform fixed ones and that rubric guidance boosts performance beyond direct supervised fine‑tuning plus RL.