@inproceedings{xu-etal-2026-checkrlm,
    title = "{C}heck{RLM}: Effective Knowledge{--}Thought Coherence Checking in Retrieval-Augmented Reasoning",
    author = "Xu, Dingling  and
      Wang, Ruobing  and
      Zhao, Qingfei  and
      Yan, Yukun  and
      Wang, Zhichun  and
      Zha, Daren  and
      Yu, Shi  and
      Liu, Zhenghao  and
      Wang, Shuo  and
      Han, Xu  and
      Sun, Maosong",
    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.1780/",
    pages = "38403--38426",
    ISBN = "979-8-89176-390-6",
    abstract = "Reasoning Language Models (RLMs) have significantly improved performance on complex tasks by extending the reasoning chain. However, these chains are prone to containing factual errors, particularly in knowledge-intensive tasks. To address this issue, we propose **CheckRLM**, a framework that improves the reliability of the reasoning process through Retrieval-Augmented Generation (RAG) by timely checking and correcting factual errors. Specifically, CheckRLM extracts factual claims from the reasoning chain to identify and localize subtle knowledge inconsistencies during inference. Upon detection of errors, a refinement mechanism performs minimal-cost yet precise corrections by leveraging external knowledge, ensuring coherence between the reasoning chain and correct knowledge. Extensive experiments demonstrate that CheckRLM substantially outperforms existing baselines, exhibiting a strong capability to mitigate error accumulation in long-horizon reasoning with lower costs. The code and data are available at https://github.com/AI9Stars/CheckRLM."
}