@inproceedings{zhen-etal-2026-hierarchical,
    title = "Hierarchical Reinforcement Learning with Augmented Step-Level Transitions for {LLM} Agents",
    author = "Zhen, Shuai  and
      Yu, Yanhua  and
      Guo, Ruopei  and
      Cheng, Nan  and
      Deng, Yang",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.318/",
    pages = "7035--7053",
    ISBN = "979-8-89176-390-6",
    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 represent *global progress* of overall task. By introducing a *local progress* module, it also iteratively and selectively summarizes interaction history within each subtask to produce a compact summary of local progress.Together, these components yield augmented step-level transitions for both high-level and low-level policies.Experimental results on ScienceWorld and ALFWorld benchmarks consistently demonstrate that STEP-HRL substantially outperforms baselines in terms of performance and generalization while reducing token usage. Our code is available at https://github.com/TonyStark042/STEP-HRL."
}