@inproceedings{wang-etal-2025-rag,
    title = "{RAG}+: Enhancing Retrieval-Augmented Generation with Application-Aware Reasoning",
    author = "Wang, Yu  and
      Zhao, Shiwan  and
      Wang, Zhihu  and
      Fan, Ming  and
      Zhang, Xicheng  and
      Zhang, Yubo  and
      Wang, Zhengfan  and
      Huang, Heyuan  and
      Liu, Ting",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.1630/",
    pages = "32001--32025",
    ISBN = "979-8-89176-332-6",
    abstract = "The integration of external knowledge through Retrieval-Augmented Generation (RAG) has become foundational in enhancing large language models (LLMs) for knowledge-intensive tasks. However, existing RAG paradigms often overlook the cognitive step of applying knowledge, leaving a gap between retrieved facts and task-specific reasoning. In this work, we introduce RAG+, a principled and modular extension that explicitly incorporates application-aware reasoning into the RAG pipeline. RAG+ constructs a dual corpus consisting of knowledge and aligned application examples, created either manually or automatically, and jointly retrieves both during inference. This design enables LLMs not only to access relevant information but also to apply it within structured, goal-oriented reasoning processes. Experiments across mathematical, law, and medical domains, conducted on multiple models, demonstrate that RAG+ consistently outperforms standard RAG variants, achieving average improvements of 3{--}5{\%}, and peak gains up to 13.5{\%} in complex scenarios. By bridging retrieval with actionable application, RAG+ advances a more cognitively grounded framework for knowledge integration, representing a step toward more interpretable and capable LLMs."
}