WebSwarm: Recursive Multi-Agent Orchestration for Deep-and-Wide Web Search

Source

Source name: arXiv
Source kind: paper
Authors / organization: Xiaoshuai Song, Liancheng Zhang, Kangzhi Zhao, Yutao Zhu, Zhongyuan Wang, Guanting Dong, Jinghan Yang, Han Li, Kun Gai, Ji-Rong Wen, Zhicheng Dou
Venue: arXiv: cs.CL
Published: 2026-07-09
Collected: 2026-07-10
URL: http://arxiv.org/abs/2607.08662v1
PDF: https://arxiv.org/pdf/2607.08662v1
DOI: UNKNOWN

Plain-Language Brief

The paper presents a new framework called WebSwarm for web search using multiple agents. This system aims to overcome the limitations of single agents by simultaneously handling depth and coverage, improving recursive depth, collaboration adaptability, and evidence-grounded expansion in complex search tasks.

What the Document Says

The paper introduces WebSwarm, a progressive recursive delegation framework for web search using large language model (LLM)-based agents.
WebSwarm dynamically instantiates agentic search nodes that solve objectives and return evidence and results to parent nodes, enabling further expansion or aggregation of the search process.
Each node can either solve its objective itself or delegate child nodes.
WebSwarm probes web organization to guide subsequent node expansion and reuses process-level experience across homogeneous sibling nodes.
The experiments show that WebSwarm outperforms single-agent and multi-agent baselines on deep, wide, and interleaved deep-and-wide tasks.
Additional analyses provide insights into the effectiveness of WebSwarm and offer suggestions for multi-agent search systems.

Key Concepts Mentioned

WebSwarm
multi-agent system
web search
large language model (LLM)
task decomposition
recursive expansion
agent collaboration
deep-and-wide search
browseComp-Plus
WideSearch
DeepWideSearch
GISA

Claims Made by the Document

WebSwarm outperforms single-agent and multi-agent baselines on deep, wide, and interleaved deep-and-wide tasks.

Evidence Used

Experiments on BrowseComp-Plus, WideSearch, DeepWideSearch, and GISA

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

Large language model (LLM)-based web search agents are transforming information seeking from simple factoid question answering into complex, deep-and-wide search and research-oriented tasks. A single ReAct-style agent is constrained by one long trajectory and limited context, making it difficult to handle depth and coverage simultaneously. Existing multi-agent systems improve search coverage through parallel execution and aggregation, but still exhibit clear limitations in recursive depth, collaboration adaptability, and evidence-grounded expansion. We propose WebSwarm, a progressive recursive delegation framework that jointly constructs task decomposition, recursive expansion, and agent collaboration during inference. WebSwarm dynamically instantiates agentic search nodes, each coupling a local objective with a search mode that specifies how the node should organize search and collaboration. Each node can either solve its objective itself or further delegate child nodes; after solving, it returns evidence and results upward, enabling parent nodes to further expand, revise, or aggregate the search process. To guide this process, WebSwarm first probes how task-relevant information is organized on the web to ground subsequent node expansion, and reuses process-level experience across homogeneous sibling nodes. Experiments on BrowseComp-Plus, WideSearch, DeepWideSearch, and GISA show that WebSwarm consistently outperforms single-agent and multi-agent baselines on deep, wide, and interleaved deep-and-wide tasks. Further analyses of ablation, task difficulty, web tool efficiency, and model generalization explain WebSwarm's effectiveness and provide insights for multi-agent search systems.