发表机构
The Chinese University of Hong Kong; The Chinese University of Hong Kong, Shenzhen; University of Oxford; York University（香港中文大学; 香港中文大学（深圳）; 牛津大学; 约克大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
JusticeAxis基准与JusticeAgent框架将法律判决形式化为参考锚定任务，通过技能蒸馏和贝叶斯验证，在256个多模态真实刑事案件中平衡刚性法条与具体情况，提升开放权重模型至商业水平。
AI 中文摘要
一个合理的判决应当将法律适用于已确定的事实，并权衡这些事实产生时的具体情况。然而，现有方法在刚性法条匹配与无依据的自由裁量之间摇摆不定，基准仅对标签或评分标准进行评分，而能够提供这种平衡的经验仍未得到验证。我们将法律判决形式化为一个以参考为锚定的任务，其目标是做出一个同时紧扣法条和具体情况的单一判决。我们引入了JusticeAxis，包含来自18个国家的256个真实刑事案件，配有音频、图像和文本证据，并为每个案件提供三份由律师撰写的判决：一份是记录在案的判决，另外两份分别对应两种失败模式。我们进一步提出了JusticeAgent，一个框架，其要素智能体负责确立事实，而法官智能体在承载具体情况经验的技能指导下适用法律。这些技能从执行轨迹中提炼，并且仅在贝叶斯可信区间内被接纳。实验表明，失败方向随规模而变化：开放权重骨干模型倾向于无依据的理由，而前沿模型则倾向于法定默认。我们进一步验证了JusticeAgent作为一个简单而有效的插件，能够将冻结的开放权重骨干模型提升到商业水平。项目资源可在该https URL获取。
英文摘要
A sound judgment applies the law to established facts and weighs the circumstances in which they arose. However, existing methods swing between rigid statute matching and ungrounded discretion, benchmarks score a label or a rubric, and the experience that would supply the balance stays unverified. We formalize legal judgment as a reference-anchored task, whose object is a single decision that stays tied to the statute and to the circumstances at once. We introduce JusticeAxis, 256 real-world criminal cases from 18 countries with audio, image, and text evidence, and three lawyer-written judgments for every case: the recorded one and one for each failure. We further propose JusticeAgent, a harness whose element agents establish the facts and whose judge agent applies the law under skills carrying experience of the circumstances. Skills are distilled from execution trajectories and admitted only under Bayesian credible bounds. Experiments show that failure turns direction with scale: open-weight backbones drift to unsupported grounds, frontier models to the statutory default. We further verify that JusticeAgent, as a simple yet effective plugin, carries a frozen open-weight backbone to commercial level. Project resources are available at https://github.com/beita6969/JusticeAxis.
