# Learning to Retrieve from Agent Trajectories Source: [Learning to Retrieve from Agent Trajectories]() Collection index: [llms.txt]() Data updated: 2026-04-11T06:00:01.369Z Authors: Yuqi Zhou, Sunhao Dai, Changle Qu, Liang Pang, Jun Xu, Ji-Rong Wen Published: 2026-03-30T17:59:02.000Z ## Abstract Information retrieval (IR) systems have traditionally been designed and trained for human users, with learning-to-rank methods relying heavily on large-scale human interaction logs such as clicks and dwell time. With the rapid emergence of large language model (LLM) powered search agents, however, retrieval is increasingly consumed by agents rather than human beings, and is embedded as a core component within multi-turn reasoning and action loops. In this setting, retrieval models trained under human-centric assumptions exhibit a fundamental mismatch with the way agents issue queries and consume results. In this work, we argue that retrieval models for agentic search should be trained directly from agent interaction data. We introduce learning to retrieve from agent trajectories as a new training paradigm, where supervision is derived from multi-step agent interactions. Through a systematic analysis of search agent trajectories, we identify key behavioral signals that reveal document utility, including browsing actions, unbrowsed rejections, and post-browse reasoning traces. Guided by these insights, we propose LRAT, a simple yet effective framework that mines high-quality retrieval supervision from agent trajectories and incorporates relevance intensity through weighted optimization. Extensive experiments on both in-domain and out-of-domain deep research benchmarks demonstrate that retrievers trained with LRAT consistently improve evidence recall, end-to-end task success, and execution efficiency across diverse agent architectures and scales. Our results highlight agent trajectories as a practical and scalable supervision source, pointing to a promising direction for retrieval in the era of agentic search. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Multi-step Reasoning on BrowseComp-Plus OOD](): Deep research agents / Multi-step reasoning; BrowseComp-Plus OOD; Success Rate (SR): 54.6. - [Multi-hop Information-Seeking on InfoSeek-Eval ID](): Multi-hop information-seeking; InfoSeek-Eval ID; Success Rate (SR): 82. ## Original sources and implementation [Original paper]() [PDF]() [Implementation]()