Adaptive iterative retrieval for enhanced retrieval-augmented generation

Existing retrieval-augmented generation (RAG) methods often treat retrieval as a one-off operation, yet recent work suggests that iteratively refining the retrieval step can yield substantial gains in relevance and downstream generation quality. However, prior iterative-retrieval approaches typically optimize only the retriever’s ranking function or only post-hoc document refinement, and they require expensive retriever retraining or complex multi-stage pipelines. To address these challenges, we propose Adaptive Iterative Retrieval for Retrieval-Augmented Generation (AIR-RAG), an adaptive, iterative retrieval framework designed to optimize both document relevance and LLM alignment within the RAG pipeline. By leveraging adaptive feedback, AIR-RAG simultaneously enhances retrieval ranking and document refinement across multiple iterations, eliminating the need for complex retraining pipelines and enabling seamless integration with existing systems. In extensive evaluations against state-of-the-art RAG methods across several benchmark datasets including TriviaQA, PopQA, HotpotQA, WikiMultiHop, PubHealth, and StrategyQA, AIR-RAG consistently demonstrates superior performance, underscoring its effectiveness in enhancing retrieval-augmented generation systems. Our code and data are available anonymously at https://github.com/aialt/AIR-RAG . • We propose AIR-RAG, an adaptive, iterative framework for RAG optimization. • AIR-RAG improves both retrieval relevance and LLM alignment without retraining. • Our method uses adaptive feedback across iterations for better document selection. • AIR-RAG integrates seamlessly with existing RAG pipelines. • Experiments show that AIR-RAG outperforms strong baselines on multiple benchmarks.