When to Retrieve During Reasoning: Adaptive Retrieval for Large Reasoning Models
在推理中何时检索:面向大推理模型的自适应检索
机构 * The University of Hong Kong(香港大学) ; Brain Investing Limited(Brain Investing有限公司) ; Stellaris AI Limited(Stellaris AI有限公司)
AI总结 本文提出ReaLM-Retrieve框架,通过三方面创新解决推理模型与检索增强生成的不匹配问题,提升答案F1分数并减少检索调用次数。
Comments 12 pages, 3 figures, 9 tables. Accepted at SIGIR 2026 (49th International ACM SIGIR Conference on Research and Development in Information Retrieval), Melbourne, Australia