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。
Zhenhailong Wang · Jiateng Liu · Amin Fazel · Ritesh Sarkhel · Xing Fan · Xiang Li · Chenlei Guo · Heng Ji · Ruhi Sarikaya
Jiateng Liu · Zhenhailong Wang · Xiaojiang Huang · Yingjie Li · Xiang Li · Chenlei Guo · Xing Fan · Ruhi Sarikaya · Heng Ji
Large language model agents rely on in-context policy documents encoding diverse business rules. As businesses scale, these documents grow, creating substantial computational overhead and motivating internalization methods that embed policy into model priors. Prior work focuses on generic prompts...
Yongchang Hao · Jie Hao · Yongsheng Mei · Ze Ye · Junyi Chai · Bin Guo · Benjamin Z. Yao · Chenlei Guo · Lili Mou
Reinforcement learning (RL) has become a cornerstone of the post-training pipeline for large language models (LLMs), enabling capabilities such as complex reasoning and tool use. However, standard RL approaches face significant challenges due to reward sparsity. Moreover, LLMs typically exhibit m...