Retrieval-augmented generation (RAG) enhances large language models (LLMs) by incorporating external knowledge, but existing approaches indiscriminately trigger retrieval and rely on single-path evidence construction, often introducing noise and limiting performance gains. In this work, we propose Decide Then Retrieve (DTR), a training-free framework that adaptively determines when retrieval is necessary and how external information should be selected. DTR leverages generation uncertainty to guide retrieval triggering and introduces a dual-path retrieval mechanism with adaptive information selection to better handle sparse and ambiguous queries. Extensive experiments across five open-domain QA benchmarks, multiple model scales, and different retrievers demonstrate that DTR consistently improves EM and F1 over standard RAG and strong retrieval-enhanced baselines, while reducing unnecessary retrievals. The code and data used in this paper are available at https://github.com/ChenWangHKU/DTR.
@article{arxiv.2601.03908,
title = {Decide Then Retrieve: A Training-Free Framework with Uncertainty-Guided Triggering and Dual-Path Retrieval},
author = {Wang Chen and Guanqiang Qi and Weikang Li and Yang Li and Deguo Xia and Jizhou Huang},
journal= {arXiv preprint arXiv:2601.03908},
year = {2026}
}