Towards Personalized Deep Research: Benchmarks and Evaluations

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liang, Yuan, Li, Jiaxian, Wang, Yuqing, Wang, Piaohong, Tian, Motong, Liu, Pai, Qiao, Shuofei, Fang, Runnan, Zhu, He, Zhang, Ge, Liu, Minghao, Jiang, Yuchen Eleanor, Zhang, Ningyu, Zhou, Wangchunshu
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908864153124864
author Liang, Yuan
Li, Jiaxian
Wang, Yuqing
Wang, Piaohong
Tian, Motong
Liu, Pai
Qiao, Shuofei
Fang, Runnan
Zhu, He
Zhang, Ge
Liu, Minghao
Jiang, Yuchen Eleanor
Zhang, Ningyu
Zhou, Wangchunshu
author_facet Liang, Yuan
Li, Jiaxian
Wang, Yuqing
Wang, Piaohong
Tian, Motong
Liu, Pai
Qiao, Shuofei
Fang, Runnan
Zhu, He
Zhang, Ge
Liu, Minghao
Jiang, Yuchen Eleanor
Zhang, Ningyu
Zhou, Wangchunshu
contents 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 (PDR-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 Personalization Alignment, Content Quality, and 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.
format Preprint
id arxiv_https___arxiv_org_abs_2509_25106
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Towards Personalized Deep Research: Benchmarks and Evaluations
Liang, Yuan
Li, Jiaxian
Wang, Yuqing
Wang, Piaohong
Tian, Motong
Liu, Pai
Qiao, Shuofei
Fang, Runnan
Zhu, He
Zhang, Ge
Liu, Minghao
Jiang, Yuchen Eleanor
Zhang, Ningyu
Zhou, Wangchunshu
Computation and Language
Artificial Intelligence
Information Retrieval
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 (PDR-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 Personalization Alignment, Content Quality, and 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.
title Towards Personalized Deep Research: Benchmarks and Evaluations
topic Computation and Language
Artificial Intelligence
Information Retrieval
url https://arxiv.org/abs/2509.25106