@inproceedings{chen-etal-2026-survey,
    title = "A Survey of Inductive Reasoning for Large Language Models",
    author = "Chen, Kedi  and
      Ruan, Dezhao  and
      Dan, Yuhao  and
      Wang, Yaoting  and
      Yan, Siyu  and
      Wu, Xuecheng  and
      Zhang, Yinqi  and
      Chen, Qin  and
      Zhou, Jie  and
      He, Liang  and
      Qi, Biqing  and
      Li, Linyang  and
      Guo, Qipeng  and
      Shi, Xiaoming  and
      Zhang, Wei",
    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.1447/",
    pages = "31356--31382",
    ISBN = "979-8-89176-390-6",
    abstract = "Reasoning is an important task for large language models (LLMs). Among all the reasoning paradigms, inductive reasoning is one of the basic types, which is characterized by its particular-to-general thinking process and the non-uniqueness of its answers. The inductive mode is crucial for knowledge generalization and aligns better with human cognition, so it is a fundamental mode of learning, hence attracting increasing interest. Despite the importance of inductive reasoning, there is no systematic summary of it. Therefore, this paper presents the first comprehensive survey of inductive reasoning for LLMs. First, methods for improving inductive reasoning are categorized into three main areas: post-training enhancement, test-time exploration, and data augmentation. Then, current benchmarks of inductive reasoning are summarized, and a unified sandbox-based evaluation approach with the observation coverage metric is derived. Finally, we offer some analyses regarding the source of inductive ability and how simple model architectures and data help with inductive tasks, providing a solid foundation for future research."
}