@inproceedings{wei-etal-2026-cirag,
    title = "{CIRAG}: Construction{--}Integration Retrieval and Adaptive Generation for Multi-hop Question Answering",
    author = "Wei, Zili  and
      Wang, Yilin  and
      Yang, Xiaocui  and
      Feng, Shi  and
      Bao, Weidong  and
      Wang, Daling  and
      Wang, Zihan  and
      Zhang, Yifei",
    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.1203/",
    pages = "26181--26197",
    ISBN = "979-8-89176-390-6",
    abstract = "Triple-based Iterative Retrieval-Augmented Generation (iRAG) mitigates document-level noise for multi-hop question answering. However, existing methods still face limitations: (i) greedy single-path expansion, which propagates early errors and fails to capture parallel evidence from different reasoning branches, and (ii) granularity{--}demand mismatch, where a single evidence representation struggles to balance noise control with contextual sufficiency. In this paper, we propose the Construction{--}Integration Retrieval and Adaptive Generation model, CIRAG. It introduces an Iterative Construction{--}Integration module that constructs candidate triples and history-conditionally integrates them to distill core triples and generate the next-hop query. This module mitigates the greedy trap by preserving multiple plausible evidence chains. Besides, to address the granularity{--}demand mismatch, we propose an Adaptive Cascaded Multi-Granularity Generation module that progressively expands contextual evidence based on the problem requirements, from triples to supporting sentences and full passages. Moreover, we introduce Trajectory Distillation, which distills the teacher model{'}s integration policy into a lightweight student, enabling efficient and reliable long-horizon reasoning. Extensive experiments demonstrate that CIRAG achieves superior performance compared to existing iRAG methods."
}