Personalized Deep Research Query Refinement with Graph-Scaffolded Evidence Grounding

2026-08-06

AI Summary

This study addresses the challenge of effectively translating user requests into personalized research specifications that encompass objectives, constraints, preferences, and evaluation criteria in deep research settings. To this end, the authors propose G-STEER, a novel approach that introduces an intent-guided graph modeling framework to capture interdependencies among specification factors. By integrating graph-scaffolded trajectory training with clarification strategy learning, G-STEER enables efficient and low-cost query personalization during the external refinement phase. The method employs a multi-source evidence decision mechanism—dynamically selecting among memory retrieval, user questioning, or direct refinement—to balance objective coverage against evidence acquisition cost. Experimental results demonstrate that G-STEER significantly improves weighted objective coverage and downstream report personalization on two deep research agents while reducing user queries to approximately one-third of those required by a strong baseline.

Abstract

User requests serve as research specifications for deep research agents, shaping what evidence to seek and how to synthesize it. In personalized deep research, these specifications must additionally reflect user goals, constraints, preferences, and evaluation criteria. User context can be incorporated either within the deep research pipeline or into the research specification provided as its input. We focus on the latter, refining the user request into a personalized research specification before passing it to an unchanged deep research agent. This requires resolving three coupled decisions: which framing factors are relevant, whether the available user context sufficiently supports them, and whether to retrieve user memory, ask the user, or stop and refine the query. For training, G-STEER organizes framing factors as elicitation targets in an Intent Elicitation Graph that captures their dependencies. It learns a clarification policy from graph-scaffolded trajectories spanning diverse factor dependencies and evidence conditions. The policy produces a refined query while balancing target coverage against the costs of evidence acquisition. Experiments show that G-STEER achieves the strongest overall weighted target coverage and the highest downstream report personalization across both evaluated DRAs, while asking roughly one third as many user questions as a strong clarification baseline.

Problem

• personalized deep research
• query refinement
• user context
• research specification
• evidence grounding

Innovation

• query refinement
• personalized deep research
• intent elicitation graph
• evidence grounding
• clarification policy