{"ID":2873437,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.06650","arxiv_id":"2509.06650","title":"Domain-Aware RAG: MoL-Enhanced RL for Efficient Training and Scalable Retrieval","abstract":"Retrieval-Augmented Generation (RAG) systems rely heavily on the retrieval stage, particularly the coarse-ranking process. Existing coarse-ranking optimization approaches often struggle to balance domain-specific knowledge learning with query enhencement, resulting in suboptimal retrieval performance. To address this challenge, we propose MoLER, a domain-aware RAG method that uses MoL-Enhanced Reinforcement Learning to optimize retrieval. MoLER has a two-stage pipeline: a continual pre-training (CPT) phase using a Mixture of Losses (MoL) to balance domain-specific knowledge with general language capabilities, and a reinforcement learning (RL) phase leveraging Group Relative Policy Optimization (GRPO) to optimize query and passage generation for maximizing document recall. A key innovation is our Multi-query Single-passage Late Fusion (MSLF) strategy, which reduces computational overhead during RL training while maintaining scalable inference via Multi-query Multi-passage Late Fusion (MMLF). Extensive experiments on benchmark datasets show that MoLER achieves state-of-the-art performance, significantly outperforming baseline methods. MoLER bridges the knowledge gap in RAG systems, enabling robust and scalable retrieval in specialized domains.","short_abstract":"Retrieval-Augmented Generation (RAG) systems rely heavily on the retrieval stage, particularly the coarse-ranking process. Existing coarse-ranking optimization approaches often struggle to balance domain-specific knowledge learning with query enhencement, resulting in suboptimal retrieval performance. To address this c...","url_abs":"https://arxiv.org/abs/2509.06650","url_pdf":"https://arxiv.org/pdf/2509.06650v1","authors":"[\"Hao Lin\",\"Peitong Xie\",\"Jingxue Chen\",\"Jie Lin\",\"Qingkun Tang\",\"Qianchun Lu\"]","published":"2025-09-08T13:04:07Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.IR\"]","methods":"[\"RAG\",\"Reinforcement Learning\"]","has_code":false}