Personalized Deep Research: A User-Centric Framework, Dataset, and Hybrid Evaluation for Knowledge Discovery

2026-05-11

AI Summary

This work addresses the limitations of existing deep research agents, which rely on static retrieval paradigms that fail to account for variations in users’ expertise and interests, often resulting in information redundancy or overload. To bridge this gap, we propose the Personalized Deep Research (PDR) framework, which dynamically integrates user context into a retrieval–reasoning loop. PDR aligns research subgoals with user intent through end-to-end integration of user profiling, iterative query generation, a two-stage retrieval process combining private and public sources, and context-aware synthesis. We further introduce the first dedicated dataset for PDR and devise a hybrid evaluation protocol that jointly assesses factual accuracy and personalized alignment. Experimental results demonstrate that PDR significantly outperforms commercial baselines across four real-world tasks, effectively narrowing the divide between generic retrieval systems and personalized knowledge acquisition.

Abstract

Deep Research agents driven by LLMs have automated the scholarly discovery pipeline, from planning and query formulation to iterative web exploration. Yet they remain constrained by a static, ``one-size-fits-all'' retrieval paradigm. Current systems fail to adaptively adjust the depth and breadth of exploration based on the user's existing expertise or latent interests, frequently resulting in reports that are either redundant for experts or overly dense for novices. To address this, we introduce Personalized Deep Research (PDR), a framework that integrates dynamic user context into the core retrieval-reasoning loop. Rather than treating personalization as a post-hoc formatting step, PDR unifies user profile modeling with iterative query development, dual-stage (private/public) retrieval, and context-aware synthesis. This allows the system to autonomously align research sub-goals with user intent and optimize the stopping criteria for evidence collection. To facilitate benchmarking, we release the PDR Dataset, covering four realistic user tasks, and propose a hybrid evaluation framework combining lexical metrics with LLM-based judgments to assess factual accuracy and personalization alignment. Experimental results against commercial baselines demonstrate that PDR significantly improves retrieval utility and report relevance, effectively bridging the gap between generic information retrieval and personalized knowledge acquisition. The resource is available to the public at https://github.com/Applied-Machine-Learning-Lab/SIGIR2026_PDR.

Problem

• personalized retrieval
• deep research
• user expertise
• adaptive exploration
• knowledge discovery

Innovation

• Personalized Deep Research
• User-Centric Retrieval
• Dynamic Context Integration
• Hybrid Evaluation
• LLM-based Knowledge Discovery