Retrieval-Augmented Generation (RAG) methods enhance LLM performance by efficiently filtering relevant context for LLMs, reducing hallucinations and inference cost. However, most existing RAG methods focus on single-step retrieval, which is often insufficient for answering complex questions that require multi-step search. Recently, multi-step retrieval approaches have emerged, typically involving the fine-tuning of small LLMs to perform multi-step retrieval. This type of fine-tuning is highly resource-intensive and does not enable the use of larger LLMs. In this work, we propose Q-RAG, a novel approach that fine-tunes the Embedder model for multi-step retrieval using reinforcement learning (RL). Q-RAG offers a competitive, resource-efficient alternative to existing multi-step retrieval methods for open-domain question answering and achieves state-of-the-art results on the popular long-context benchmarks BabiLong and RULER for contexts up to 10M tokens. Code is available at https://github.com/griver/Q-RAG
@article{arxiv.2511.07328,
title = {Q-RAG: Long Context Multi-step Retrieval via Value-based Embedder Training},
author = {Artyom Sorokin and Nazar Buzun and Alexander Anokhin and Oleg Inozemcev and Egor Vedernikov and Petr Anokhin and Mikhail Burtsev and Trushkov Alexey and Yin Wenshuai and Evgeny Burnaev},
journal= {arXiv preprint arXiv:2511.07328},
year = {2026}
}
Comments
Published as a conference paper at ICLR 2026. Code is available at https://github.com/griver/Q-RAG