Towards Personalized Deep Research: Benchmarks and Evaluations
This work addresses the problem of evaluating personalized AI research assistants for developers and researchers, but it is incremental as it builds on existing DRA concepts by adding a new benchmark.
The paper tackled the lack of benchmarks for evaluating personalization in Deep Research Agents (DRAs) by introducing Personalized Deep Research Bench, which includes 50 tasks across 10 domains paired with 25 user profiles to create 250 queries, and proposed the PQR Evaluation Framework to measure personalization, quality, and reliability.
Deep Research Agents (DRAs) can autonomously conduct complex investigations and generate comprehensive reports, demonstrating strong real-world potential. However, existing evaluations mostly rely on close-ended benchmarks, while open-ended deep research benchmarks remain scarce and typically neglect personalized scenarios. To bridge this gap, we introduce Personalized Deep Research Bench, the first benchmark for evaluating personalization in DRAs. It pairs 50 diverse research tasks across 10 domains with 25 authentic user profiles that combine structured persona attributes with dynamic real-world contexts, yielding 250 realistic user-task queries. To assess system performance, we propose the PQR Evaluation Framework, which jointly measures (P) Personalization Alignment, (Q) Content Quality, and (R) Factual Reliability. Our experiments on a range of systems highlight current capabilities and limitations in handling personalized deep research. This work establishes a rigorous foundation for developing and evaluating the next generation of truly personalized AI research assistants.