@inproceedings{wang-etal-2025-meta,
    title = "Meta-Reflection: A Feedback-Free Reflection Learning Framework",
    author = "Wang, Yaoke  and
      Zhu, Yun  and
      XintongBao, XintongBao  and
      Zhang, Wenqiao  and
      Dai, Suyang  and
      Chen, Kehan  and
      Li, Wenqiang  and
      Huang, Gang  and
      Tang, Siliang  and
      Zhuang, Yueting",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.acl-long.201/",
    pages = "3958--3976",
    ISBN = "979-8-89176-251-0",
    abstract = "Despite the remarkable capabilities of large language models (LLMs) in natural language understanding and reasoning, they often display undesirable behaviors, such as generating hallucinations and unfaithful reasoning. A prevalent strategy to mitigate these issues is the use of reflection, which refines responses through an iterative process. However, while promising, reflection heavily relies on high-quality external feedback and requires iterative multi-agent inference processes, thus hindering its practical application. In this paper, we propose Meta-Reflection, a novel feedback-free reflection mechanism that necessitates only a single inference pass without external feedback. Motivated by the human ability to remember and retrieve reflections from past experiences when encountering similar problems, Meta-Reflection integrates reflective insights into a codebook, allowing the historical insights to be stored, retrieved, and used to guide LLMs in problem-solving. To thoroughly investigate and evaluate the practicality of Meta-Reflection in real-world scenarios, we introduce an industrial e-commerce benchmark named E-commerce Customer Intent Detection. Extensive experiments conducted on both public datasets and the ECID benchmark highlight the effectiveness and efficiency of our proposed approach. Project is available at https://github.com/DCDmllm/Meta-Reflection"
}