Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Lee, Ka Yiu, Huang, Yuxuan, He, Zhiyuan, Zhou, Huichi, Luo, Weilin, Shao, Kun, Fang, Meng, Wang, Jun
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2604.02971
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866918426552827904
author Lee, Ka Yiu
Huang, Yuxuan
He, Zhiyuan
Zhou, Huichi
Luo, Weilin
Shao, Kun
Fang, Meng
Wang, Jun
author_facet Lee, Ka Yiu
Huang, Yuxuan
He, Zhiyuan
Zhou, Huichi
Luo, Weilin
Shao, Kun
Fang, Meng
Wang, Jun
contents Recent agentic search systems have made substantial progress by emphasising deep, multi-step reasoning. However, this focus often overlooks the challenges of wide-scale information synthesis, where agents must aggregate large volumes of heterogeneous evidence across many sources. As a result, most existing large language model agent systems face severe limitations in data-intensive settings, including context saturation, cascading error propagation, and high end-to-end latency. To address these challenges, we present \framework, a hierarchical framework based on principle of near-decomposability, containing a strategic \textit{Host}, multiple \textit{Managers} and parallel \textit{Workers}. By leveraging aggregation and reflection mechanisms at the Manager layer, our framework enforces strict context isolation to prevent saturation and error propagation. Simultaneously, the parallelism in worker layer accelerates the speed of overall task execution, mitigating the significant latency. Our evaluation on two complementary benchmarks demonstrates both efficiency ($ 3-5 \times$ speed-up) and effectiveness, achieving a $8.4\%$ success rate on WideSearch-en and $52.9\%$ accuracy on BrowseComp-zh. The code is released at https://github.com/agent-on-the-fly/InfoSeeker
format Preprint
id arxiv_https___arxiv_org_abs_2604_02971
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle InfoSeeker: A Scalable Hierarchical Parallel Agent Framework for Web Information Seeking
Lee, Ka Yiu
Huang, Yuxuan
He, Zhiyuan
Zhou, Huichi
Luo, Weilin
Shao, Kun
Fang, Meng
Wang, Jun
Artificial Intelligence
Recent agentic search systems have made substantial progress by emphasising deep, multi-step reasoning. However, this focus often overlooks the challenges of wide-scale information synthesis, where agents must aggregate large volumes of heterogeneous evidence across many sources. As a result, most existing large language model agent systems face severe limitations in data-intensive settings, including context saturation, cascading error propagation, and high end-to-end latency. To address these challenges, we present \framework, a hierarchical framework based on principle of near-decomposability, containing a strategic \textit{Host}, multiple \textit{Managers} and parallel \textit{Workers}. By leveraging aggregation and reflection mechanisms at the Manager layer, our framework enforces strict context isolation to prevent saturation and error propagation. Simultaneously, the parallelism in worker layer accelerates the speed of overall task execution, mitigating the significant latency. Our evaluation on two complementary benchmarks demonstrates both efficiency ($ 3-5 \times$ speed-up) and effectiveness, achieving a $8.4\%$ success rate on WideSearch-en and $52.9\%$ accuracy on BrowseComp-zh. The code is released at https://github.com/agent-on-the-fly/InfoSeeker
title InfoSeeker: A Scalable Hierarchical Parallel Agent Framework for Web Information Seeking
topic Artificial Intelligence
url https://arxiv.org/abs/2604.02971