Abstract
Deep research (DR) systems are increasingly used for complex information-seeking tasks, but existing works mainly focus on generating reports and summaries. In contrast, many enterprise tasks require an agent to identify concrete workflows, which is a sequence of action-steps. For example, rather than summarizing budgeting policies, an agent should determine the steps needed to answer a question such as: "How do I request new headcount given a fixed budget?"
Therefore, we introduce DRFLOW, a benchmark for evaluating personalized workflows predicted by agents from heterogeneous sources. Each task requires the agent to identify relevant evidence from scattered sources, then use that evidence to predict the correct action-step sequence for the user's task. DRFLOW contains 100 tasks across five domains, with 1,246 reference workflow steps grounded in more than 3,900 sources.
We define seven diagnostic metrics covering factual grounding, step recovery, structural ordering, condition resolution, and personalization. We further present DRFLOW-Agent (DRFA), a workflow-oriented reference agent to predict personalized workflow. We show that although DRFA improves over strong baseline agents (up to 10.02% average F1 score), there remains substantial room for improvement across these workflow metrics, indicating that predicting complete and correct personalized workflows remains a challenging frontier for deep research.
Blogger's Review: The introduction of DRFLOW offers a fresh perspective on personalized workflow research, emphasizing the importance of extracting and integrating information from heterogeneous data sources. The diversity and complexity of this benchmark will drive further exploration in related fields, making its future development and improvements worthy of attention.