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

TL;DR

This paper introduces Personalized Deep Research (PDR), a user-centric framework for knowledge discovery that dynamically adapts retrieval and synthesis based on user context, improving relevance and personalization.

Contribution

The paper presents PDR, a novel framework integrating user profiles into research agents, along with a new dataset and evaluation method for personalized scholarly discovery.

Findings

PDR outperforms commercial baselines in retrieval utility.

PDR enhances report relevance and personalization.

The PDR dataset enables benchmarking of personalized research systems.

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.