作者位次 #4/5ACL 2026Poster· Natural Language Processing
Hierarchical Reinforcement Learning with Augmented Step-Level Transitions for LLM Agents
Shuai Zhen · Yanhua Yu · Ruopei Guo · Nan Cheng · Yang Deng
摘要
Large language model (LLM) agents have demonstrated strong capabilities in complex interactive decision-making tasks. However, existing LLM agents typically rely on increasingly long interaction histories, resulting in high computational cost and limited scalability. In this paper, we propose STE...