Large language models have demonstrated impressive reasoning capabilities but are inherently limited by their knowledge reservoir. Retrieval-augmented reasoning mitigates this limitation by allowing LLMs to query external resources, but existing methods often retrieve irrelevant or noisy information, hindering accurate reasoning. In this paper, we propose AutoRefine, a reinforcement learning post-training framework that adopts a new ``search-and-refine-during-think'' paradigm. AutoRefine introduces explicit knowledge refinement steps between successive search calls, enabling the model to iteratively filter, distill, and organize evidence before generating an answer. Furthermore, we incorporate tailored retrieval-specific rewards alongside answer correctness rewards using group relative policy optimization. Experiments on single-hop and multi-hop QA benchmarks demonstrate that AutoRefine significantly outperforms existing approaches, particularly in complex, multi-hop reasoning scenarios. Detailed analysis shows that AutoRefine issues frequent, higher-quality searches and synthesizes evidence effectively.
View on arXiv@article{shi2025_2505.11277,
title={ Search and Refine During Think: Autonomous Retrieval-Augmented Reasoning of LLMs },
author={ Yaorui Shi and Shihan Li and Chang Wu and Zhiyuan Liu and Junfeng Fang and Hengxing Cai and An Zhang and Xiang Wang },
journal={arXiv preprint arXiv:2505.11277},
year={ 2025 }
}