When Deep Research Agents Stagnate: Enhancing Reasoning with Retrieval-Aware Agent Control
TL;DR
A set of unsupervised signals and a Retrieval-Aware Agent Controller (RAAC) are introduced, which assists the agent in selecting optimal actions at each stage of the research process, resulting in more effective reasoning trajectories that improve overall performance while reducing unnecessary iterations, and consequently cost and latency.
Abstract
In this paper, we analyze the reasoning trajectories of a variety of DRAs and show that existing agents often suffer from reasoning stagnation: the majority of iterations contribute little or no improvement to final performance, while agents lack awareness of their trajectories and are therefore ineffective at adapting their search strategies or determining when to terminate. To address this issue, we introduce a set of unsupervised signals and a Retrieval-Aware Agent Controller (RAAC), which assists the agent in selecting optimal actions at each stage of the research process. RAAC incorporates key information retrieval principles, namely search novelty and information coverage, resulting in more effective reasoning trajectories that improve overall performance while reducing unnecessary iterations, and consequently cost and latency. Specifically on BrowseComp-Plus and across a large set of DRAs, adding RAAC reduces the number of search calls by an average of 14, significantly improves the best-performing DRA on recall and accuracy, and achieves an accuracy gain of up to 10% (3% on average).