Adaptive Retrieval for Reasoning-Intensive Retrieval
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.
Cite
@article{arxiv.2601.04618,
title = {Adaptive Retrieval for Reasoning-Intensive Retrieval},
author = {Jongho Kim and Jaeyoung Kim and Seung-won Hwang and Jihyuk Kim and Yu Jin Kim and Moontae Lee},
journal= {arXiv preprint arXiv:2601.04618},
year = {2026}
}
Comments
This document was submitted without obtaining all necessary permissions from our institutions and therefore needs to be withdrawn. We require additional internal review and approval prior to public release. The corresponding author apologizes for any inconvenience this might cause