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

Researchers propose a new framework called WebSwarm for deep and wide web searches using large language models (LLMs). The framework aims to improve the ability of single agents to handle complexity and coverage simultaneously, which is a limitation in current systems. WebSwarm does this by dynamically creating search nodes that can collaborate and expand recursively based on task-relevant information found on the web.

What the Document Says

• The text discusses a new framework called WebSwarm for deep and wide web searches using LLMs.
• WebSwarm aims to improve the ability of single agents to handle depth and coverage simultaneously.
• The framework uses search nodes that can collaborate and expand recursively based on task-relevant information found on the web.
• Experiments show that WebSwarm outperforms single-agent and multi-agent baselines on deep, wide, and interleaved deep-and-wide tasks.

Key Concepts Mentioned

• WebSwarm
• large language models (LLMs)
• deep and wide web searches
• search nodes
• task-relevant information
• experiments

Claims Made by the Document

• WebSwarm improves the ability of single agents to handle depth and coverage simultaneously.
• WebSwarm outperforms single-agent and multi-agent baselines on deep, wide, and interleaved deep-and-wide tasks.

Evidence Used

• The text states that WebSwarm 'consistently outperforms single-agent and multi-agent baselines' in experiments.

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.