arXiv 2509.248692025-10-12cs.IRcs.AIcs.CL

Retro*：针对推理密集型文档检索的 LLMs 优化

Retro*: Optimizing LLMs for Reasoning-Intensive Document Retrieval

University of Science and Technology of China（中国科学技术大学）；Beijing Academy of Artificial Intelligence（北京人工智能研究院）；Beijing University of Posts and Telecommunications（北京邮电大学）；State Key Laboratory of Cognitive Intelligence（认知智能国家重点实验室）；Hong Kong Polytechnic University（香港理工大学）；Hong Kong University of Science and Technology（香港科技大学）

Junwei Lan, Jianlyu Chen, Zheng Liu, Chaofan Li, Siqi Bao, Defu Lian

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

提出Retro*方法用于推理密集型文档检索，通过基于评分标准的相关性打分机制、测试时扩展及新型强化学习算法优化LLM推理，在BRIGHT基准上取得最优性能。

摘要：

随着 LLM agents 和 RAG 的日益普及，检索对解决任务至关重要的文档变得越来越重要，即使这些文档与任务的联系是间接或隐式的。解决这个问题需要进行细粒度推理，以准确评估任务与每个候选文档之间的相关性。然而，这种能力对现有的 IR 技术构成了重大挑战。尽管在 reasoning-enhanced IR 方面取得了最新进展，但现有方法在适用性、可扩展性和效率方面仍面临重大挑战。在这项工作中，我们提出了一种用于推理密集型文档检索的新方法 Retro*。该方法引入了一种基于评分标准的相关性打分机制，使模型能够基于明确定义的标准来推理任务与文档之间的关系，从而生成细粒度且可解释的相关性分数。Retro* 还通过分数整合结合多条推理轨迹来支持测试时扩展，从而产生更可靠的相关性估计。为了优化 Retro* 的推理能力，我们引入了一种针对其相关性打分机制量身定制的新型强化学习算法，该算法采用两种复合奖励来充分利用每个训练样本的轨迹。我们的实验表明，Retro* 优于现有的文档检索方法并具有显著优势，在 BRIGHT 基准上实现了最先进的性能。

英文摘要：

With the growing popularity of LLM agents and RAG, it has become increasingly important to retrieve documents that are essential for solving a task, even when their connection to the task is indirect or implicit. Addressing this problem requires fine-grained reasoning to accurately assess the relevance between the task and each candidate document. This capability, however, poses a significant challenge for existing IR techniques. Despite recent progress in reasoning-enhanced IR, existing approaches still face significant challenges in applicability, scalability, and efficiency. In this work, we propose Retro*, a novel approach for reasoning-intensive document retrieval. Our method introduces a rubric-based relevance scoring mechanism, enabling the model to reason about the relationship between a task and a document based on explicitly defined criteria, whereby producing a fine-grained, interpretable relevance score. Retro* also supports test-time scaling by combining multiple reasoning trajectories via score integration, which produces more reliable relevance estimates. To optimize Retro*'s reasoning capabilities, we introduce a novel reinforcement learning algorithm tailored for its relevance scoring mechanism, which employs two composite rewards to fully exploit the trajectories of each training sample. Our experiments show that Retro* outperforms existing document retrieval methods with notable advantages, leading to state-of-the-art performance on the BRIGHT benchmark.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。