Hierarchical Reinforcement Learning with Augmented Step-Level Transitions for LLM Agents

评分 6.4 · 来源：cs.AI updates on arXiv.org · 发布于 2026-04-08

评分依据：有一定参考价值的AI研究论文

arXiv:2604.05808v1 Announce Type: new Abstract: 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 STEP-HRL, a hierarchical reinforcement learning (HRL) framework that enables step-level learning by conditioning only on single-step transitions rather than full interaction histories. STEP-HRL structures tasks hierarchically, using completed subtasks to rep