作者位次 #2/3ICLR 2026Poster· Reinforcement Learning / Online
RuleReasoner: Reinforced Rule-based Reasoning via Domain-aware Dynamic Sampling
Yang Liu · Jiaqi Li · Zilong Zheng
首次获取该候选人的完整档案及 StartLux 评估共 20 积分；每位用户单独解锁，之后查看免费。主动刷新 20 积分。
实时查找电子邮箱，费用不超过20积分；未找到邮箱不扣费。
Yang Liu · Jiaqi Li · Zilong Zheng
Ziang Chen · Guannan Li · Fanlin Ji · Yipeng Kang · Jiaqi Li · Muhan Zhang · Yangtao Zhang · Li Tianjiao · Jiannan Wang · Xin Guo · Song-Chun Zhu · Bin Ling
Large Language Models (LLMs) have demonstrated strong cross-domain capabilities, yet their competence in specialized professional tasks remains underexamined. Existing legal benchmarks evaluate isolated tasks or exam-style questions, failing to capture the procedural interdependencies and adjudic...