把数学AI的“LLM提案、验证器把关”范式搬进法律领域，用形式化验证打造可验证的奖励信号，法律AI自改进的新路子。
arXiv:2606.23913v1 Announce Type: new Abstract: This article develops an architecture that creates a formally verifiable reward signal to train legal …
CATPO方法通过批评增强的树策略优化，显著提升大语言模型推理中的密集奖励获取效率。
arXiv:2606.08346v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has become a dominant paradigm for improving t…
提出Cross-Model Entropy方法，免去人工标注，以模型间交叉熵驱动强化学习后训练，突破奖励信号瓶颈。
arXiv:2605.29009v1 Announce Type: cross Abstract: Post-training large language models with reinforcement learning is bottlenecked by the reward signal…
通过视觉推理提升过程奖励建模精度，为复杂任务训练提供新思路。
arXiv:2508.03556v3 Announce Type: replace Abstract: Process Reward Model (PRM) is widely used in the post-training of Large Language Model (LLM) becau…
揭秘大模型对齐中隐藏的奖励目标，帮你避开「未知的未知」对齐陷阱
arXiv:2602.15338v2 Announce Type: replace-cross Abstract: Large language model (LLM) alignment relies on complex reward signals that often obscure the…