A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Xi, Yunjia, Lin, Jianghao, Xiao, Yongzhao, Zhou, Zheli, Shan, Rong, Gao, Te, Zhu, Jiachen, Liu, Weiwen, Yu, Yong, Zhang, Weinan
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912543424905216
author Xi, Yunjia
Lin, Jianghao
Xiao, Yongzhao
Zhou, Zheli
Shan, Rong
Gao, Te
Zhu, Jiachen
Liu, Weiwen
Yu, Yong
Zhang, Weinan
author_facet Xi, Yunjia
Lin, Jianghao
Xiao, Yongzhao
Zhou, Zheli
Shan, Rong
Gao, Te
Zhu, Jiachen
Liu, Weiwen
Yu, Yong
Zhang, Weinan
contents The advent of Large Language Models (LLMs) has significantly revolutionized web search. The emergence of LLM-based Search Agents marks a pivotal shift towards deeper, dynamic, autonomous information seeking. These agents can comprehend user intentions and environmental context and execute multi-turn retrieval with dynamic planning, extending search capabilities far beyond the web. Leading examples like OpenAI's Deep Research highlight their potential for deep information mining and real-world applications. This survey provides the first systematic analysis of search agents. We comprehensively analyze and categorize existing works from the perspectives of architecture, optimization, application, and evaluation, ultimately identifying critical open challenges and outlining promising future research directions in this rapidly evolving field. Our repository is available on https://github.com/YunjiaXi/Awesome-Search-Agent-Papers.
format Preprint
id arxiv_https___arxiv_org_abs_2508_05668
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges
Xi, Yunjia
Lin, Jianghao
Xiao, Yongzhao
Zhou, Zheli
Shan, Rong
Gao, Te
Zhu, Jiachen
Liu, Weiwen
Yu, Yong
Zhang, Weinan
Information Retrieval
Artificial Intelligence
Computation and Language
The advent of Large Language Models (LLMs) has significantly revolutionized web search. The emergence of LLM-based Search Agents marks a pivotal shift towards deeper, dynamic, autonomous information seeking. These agents can comprehend user intentions and environmental context and execute multi-turn retrieval with dynamic planning, extending search capabilities far beyond the web. Leading examples like OpenAI's Deep Research highlight their potential for deep information mining and real-world applications. This survey provides the first systematic analysis of search agents. We comprehensively analyze and categorize existing works from the perspectives of architecture, optimization, application, and evaluation, ultimately identifying critical open challenges and outlining promising future research directions in this rapidly evolving field. Our repository is available on https://github.com/YunjiaXi/Awesome-Search-Agent-Papers.
title A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges
topic Information Retrieval
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2508.05668