InfoSeeker: A Scalable Hierarchical Parallel Agent Framework for Web Information Seeking

TL;DR

InfoSeeker introduces a hierarchical agent framework that enhances web information seeking by improving scalability, speed, and accuracy through parallelism and strategic aggregation, addressing limitations of existing large language model agents.

Contribution

The paper presents a novel hierarchical framework with Host, Managers, and Workers that improves data synthesis, reduces latency, and prevents error propagation in large-scale web information seeking.

Findings

Achieved 3-5x speed-up in task execution.

Demonstrated 8.4% success rate on WideSearch-en.

Achieved 52.9% accuracy on BrowseComp-zh.

Abstract

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