@inproceedings{sun-etal-2026-learning,
    title = "Learning from Cognition: Enhancing {RL} Efficiency for {LLM} Reasoning via Hierarchical Metacognitive Decomposition and Refinement",
    author = "Sun, Zexu  and
      Zeng, Yongcheng  and
      Min, Erxue  and
      Gao, Heyang  and
      Ji, Bokai  and
      Liu, Dugang  and
      Tang, Xing  and
      He, Xiuqiang  and
      Chen, Xu",
    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.1022/",
    pages = "22331--22348",
    ISBN = "979-8-89176-390-6",
    abstract = "Contemporary progress in Large Language Models (LLMs) has revealed notable inferential capacities via reinforcement learning (RL) employing verifiable rewards. However, ``zero-RL'' approaches relying on fixed prompt templates introduce substantial sampling inefficiencies for weak LLMs, as most problems generate invalid outputs during accuracy-driven filtration. To solve this, we propose Cog-Rethinker, a novel hierarchical metacognitive RL framework. Cog-Rethinker enhances the rollout procedure by improving sample utilization through a two-stage framework leveraging human cognition. First, it prompts the policy to decompose zero-accuracy problems into subproblems. Second, it prompts the policy to refine answers by referencing previous wrong solutions. Moreover, to enable cold-starts and maintain train-test consistency, Cog-Rethinker applies supervised fine-tuning using correct samples from these stages. Experimental results demonstrate Cog-Rethinker{'}s superior performance on mathematical reasoning benchmarks and its improved sample efficiency that accelerates convergence compared to baselines."
}