@inproceedings{kim-etal-2026-adaptive,
    title = "Adaptive Retrieval for Reasoning",
    author = "Kim, Jongho  and
      Kim, Jaeyoung  and
      Kim, Jihyuk  and
      Kim, Yu Jin  and
      Hwang, Seung-won  and
      Lee, Moontae",
    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.1734/",
    pages = "37366--37381",
    ISBN = "979-8-89176-390-6",
    abstract = "We study leveraging adaptive retrieval to ensure sufficient ``bridge'' documents are retrieved for reasoning-intensive retrieval. Bridge documents are those that contribute to the reasoning process yet are not directly relevant to the initial query. While existing reasoning-based reranker pipelines attempt to surface these documents in ranking, they suffer from bounded recall. Naive solution with adaptive retrieval into these pipelines often leads to planning error propagation. To address this, we propose REPAIR, a framework that bridges this gap by repurposing reasoning plans as dense feedback signals for adaptive retrieval. Our key distinction is enabling mid-course correction during reranking through selective adaptive retrieval, retrieving documents that support the pivotal plan. Experimental results on reasoning-intensive retrieval and complex QA tasks demonstrate that our method outperforms existing baselines by 5.6{\%}pt."
}