@inproceedings{li-etal-2026-multi,
    title = "Multi-Hop Knowledge Editing via Critic-Guided Multi-Agent Reasoning",
    author = "Li, Xudong  and
      Tian, Yuhang  and
      Song, Dandan  and
      Wu, Zhijing  and
      Zhang, Shuhao  and
      Yang, Jun  and
      Huo, Yongyu  and
      Zhou, Changzhi  and
      Zhang, Xinyu  and
      Li, Chenhao  and
      Ma, Huipeng  and
      Zhang, Luan  and
      Xu, Yan  and
      Liu, Qian",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.853/",
    pages = "17259--17276",
    ISBN = "979-8-89176-395-1",
    abstract = "Knowledge within large language models (LLMs) inevitably lags behind an evolving world, motivating knowledge editing methods that update facts without expensive retraining. In multi-hop knowledge editing, models must not only recall updated facts but also correctly propagate them through multi-step reasoning chains. However, most existing approaches rely on unidirectional, feed-forward pipelines, decomposing questions and retrieving edited facts in a rigid hop-wise sequence. This design is brittle: a minor retrieval error or logical mismatch at an early hop can become a silent failure that cascades to the final answer without an explicit recovery mechanism. To address this limitation, we propose Critic-Guided Multi-Agent Reasoning for Knowledge Editing (CARE), a framework for closed-loop post-edit reasoning. A Critic agent performs chain-level verification by checking both global coherence and step-wise correctness, and triggers bounded backtracking for iterative self-correction, while a Selector agent supplies high-fidelity, low-noise candidate pools from the edit store to enable effective revision. Experiments on MQuAKE-2002 and MQuAKE-hard demonstrate that CARE effectively mitigates error propagation, achieving a new state-of-the-art."
}