菜单

关于 🐙 GitHub
arXiv 提交日期: 2026-06-17
📄 Abstract - 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. We present LegalWorld, a life-cycle interactive environment that models Chinese civil litigation as a causally connected state chain of five stages (seven sub-scenarios), grounded in 75,309 paired Chinese civil judgments. We pair it with reusable infrastructure (local memory, global case memory, a Skill/Tool library) that keeps each dispute consistent across its full life cycle. Building on this environment, we construct LongJud-Bench to evaluate agent capability across all five connected stages. 18,992 ratings from 217 legal-background evaluators confirm that LegalWorld trajectories are procedurally faithful and role-consistent; and a capability-level cross-model evaluation reveals sharp divergences that aggregate scores cannot expose, with no single backbone leading across consultation, drafting, and courtroom advocacy. Detailed resources will be released publicly.

顶级标签: llm agents benchmark
详细标签: legal agents life-cycle simulation civil litigation cross-stage evaluation legal benchmark 或 搜索:

LegalWorld:面向法律智能体的全生命周期交互环境 / LegalWorld: A Life-Cycle Interactive Environment for Legal Agents


1️⃣ 一句话总结

本文提出一个名为LegalWorld的仿真环境,能够模拟中国民事诉讼从立案到庭审的完整流程,并配套构建了相应的评测基准,从而解决了现有法律AI只能处理孤立任务、无法捕获阶段间因果依赖的问题。

源自 arXiv: 2606.18728