Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
October 20, 2025Open Access

Towards Personalized Deep Research: Benchmarks and Evaluations

View Full Paper
Ask AI
Bookmark
Share

Authors

YLYuan LiangJLJ.X. LiYWYuqing Wang

Discussion

Loading...

Member takes

Overview

Introducing a new benchmark for evaluating personalization in deep research agents, highlighting gaps in current assessments.

Key Points

  • The Personalized Deep Research Bench targets evaluations of deep research agents by introducing realistic user profiles.
  • The PQR Evaluation Framework assesses system performance focusing on personalization alignment, content quality, and factual reliability.
  • Experiments conducted on various systems reveal limitations in addressing personalized queries while indicating existing capabilities.
  • This work lays the groundwork for the development and evaluation of future personalized AI research assistants.

Cite This Study

Liang et al. (2025) studied this question.

synapsesocial.com/papers/68f5fcd68d54a28a75cf1e4fhttps://doi.org/10.48550/arxiv.2509.25106
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1A Rigorous Benchmark with Multidimensional Evaluation for Deep Research Agents: From Answers to Reports2025
  2. 2DRBench: A Realistic Benchmark for Enterprise Deep Research2025
  3. 3Beyond Static Evaluation: Rethinking the Assessment of Personalized Agent Adaptability in Information Retrieval2025 · 1 citations
  4. 4PersonaFeedback: A Large-scale Human-annotated Benchmark For Personalization2025
  5. 5Deep Research: A Survey of Autonomous Research Agents2025 · 1 citations