Recent research highlights the challenges retrieval models face in retrieving useful contexts and the limitations of generation models in effectively utilizing those contexts in retrieval-augmented generation (RAG) settings. To address these challenges, we introduce RAG-RL, the first reasoning language model (RLM) specifically trained for RAG. RAG-RL demonstrates that stronger answer generation models can identify relevant contexts within larger sets of retrieved information -- thereby alleviating the burden on retrievers -- while also being able to utilize those contexts more effectively. Moreover, we show that curriculum design in the reinforcement learning (RL) post-training process is a powerful approach to enhancing model performance. We benchmark our method on two open-domain question-answering datasets and achieve state-of-the-art results, surpassing previous SOTA generative reader models. In addition, we offers empirical insights into various curriculum learning strategies, providing a deeper understanding of their impact on model performance.
View on arXiv@article{huang2025_2503.12759,
title={ RAG-RL: Advancing Retrieval-Augmented Generation via RL and Curriculum Learning },
author={ Jerry Huang and Siddarth Madala and Risham Sidhu and Cheng Niu and Julia Hockenmaier and Tong Zhang },
journal={arXiv preprint arXiv:2503.12759},
year={ 2025 }
}