作者位次 #4/9ACL 2026Poster· ACL Industry Track
VEG : Verbal \epsilon -greedy for Semantic Exploration in Multi-Turn RL Agents
Yongchang Hao · Jie Hao · Yongsheng Mei · Ze Ye · Junyi Chai · Bin Guo · Benjamin Z. Yao · Chenlei Guo · Lili Mou
摘要
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...