Reasoning-conditioned embeddings can improve retrieval by progressively refining semantic constraints. However, additional reasoning may introduce over-generalized or semantically noisy abstractions that weaken retrieval specificity. Existing methods largely supervise reasoning through final retrieval outcomes, providing limited guidance over the refinement process itself. We propose AURA, a framework that directly supervises intermediate reasoning states according to how well they separate relevant documents from hard distractors. AURA further trains a lightweight utility estimator over prefix-conditioned embeddings to adapt reasoning depth at inference time. On the reasoning-intensive BRIGHT benchmark, AURA-4B achieves 34.7 average nDCG@10 while using 2.8 reasoning steps and 96 generated tokens per query. Under matched deployment conditions, adaptive stopping reduces latency from 4.6 to 0.76 seconds relative to full-trajectory reasoning. Results on MS MARCO further suggest that this specialization need not substantially degrade conventional in-domain retrieval.
DeepRAG: Thinking to Retrieve Step by Step for Large Language Models
Chinese Information Processing Laboratory, Institute of Software, Chinese Academy of Sciences(中国科学院软件研究所信息处理实验室);University of Chinese Academy of Sciences(中国科学院大学);Pattern Recognition Center, WeChat AI, Tencent Inc, China(腾讯人工智能部模式识别中心)
Utility-Focused LLM Annotation for Retrieval and Retrieval-Augmented Generation
State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences(中国科学院人工智能安全国家重点实验室,计算技术研究所);University of Chinese Academy of Sciences(中国科学院大学);Baidu Inc.(百度公司)
From Relevance to Utility: Evidence Retrieval with Feedback for Fact Verification
University of Chinese Academy of Sciences(中国科学院大学);Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所);University of Amsterdam(阿姆斯特丹大学)
LLM-Specific Utility for Retrieval-Augmented Generation
State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences(人工智能安全国家重点实验室,计算技术研究所,中国科学院);University of Chinese Academy of Sciences(中国科学院大学);Baidu Inc(百度公司)
Distilling a Small Utility-Based Passage Selector to Enhance Retrieval-Augmented Generation
State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences(人工智能安全国家重点实验室,计算技术研究所,中国科学院);University of Chinese Academy of Sciences(中国科学院大学);Baidu Inc(百度公司)
An Iterative Utility Judgment Framework Inspired by Philosophical Relevance via LLMs
State Key Laboratory of AI Safety(人工智能安全国家重点实验室);Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所);University of Chinese Academy of Sciences(中国科学院大学)
IRGAN: A Minimax Game for Unifying Generative and Discriminative Information Retrieval Models
University College London(伦敦大学学院);Shanghai Jiao Tong University(上海交通大学);Alibaba Group(阿里巴巴集团);Tianjin University(天津大学);Birkbeck, University of London(伦敦大学伯贝克学院)
Comparing the Utility, Preference, and Performance of Course Material Search Functionality and Retrieval-Augmented Generation Large Language Model (RAG-LLM) AI Chatbots in Information-Seeking Tasks
Generative vector search to improve pathology foundation models across multimodal vision-language tasks
Science for Life Laboratory, School of Engineering Sciences in Chemistry, Biotechnology, and Health, Royal Institute of Technology – KTH(皇家理工学院);Department of Microbiology, Tumor and Cell Biology, Karolinska Institutet(卡罗林斯卡学院)