{"ID":6267278,"CreatedAt":"2026-07-10T01:11:38.759438437Z","UpdatedAt":"2026-07-13T01:02:08.706470581Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.08662","arxiv_id":"2607.08662","title":"WebSwarm: Recursive Multi-Agent Orchestration for Deep-and-Wide Web Search","abstract":"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.","short_abstract":"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 cov...","url_abs":"https://arxiv.org/abs/2607.08662","url_pdf":"https://arxiv.org/pdf/2607.08662v1","authors":"[\"Xiaoshuai Song\",\"Liancheng Zhang\",\"Kangzhi Zhao\",\"Yutao Zhu\",\"Zhongyuan Wang\",\"Guanting Dong\",\"Jinghan Yang\",\"Han Li\",\"Kun Gai\",\"Ji-Rong Wen\",\"Zhicheng Dou\"]","published":"2026-07-09T16:28:49Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\",\"cs.MA\"]","methods":"[\"Large Language Model\",\"Language Model\",\"Generative Adversarial Network\"]","has_code":false}