---
title: "WebSwarm：用于深度与广度网页搜索的递归多智能体编排框架"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2607.08662v1"
permalink: "https://feed.astralor.com/items/itm_ce8fdbfde4c93860659929e8"
published: "2026-07-09T16:28:49.000Z"
score: 78
channel: "ai"
tags: ["WebSwarm","多智能体系统","大型语言模型","网页搜索","递归委托"]
---

# WebSwarm：用于深度与广度网页搜索的递归多智能体编排框架

## AI 点评

> 这篇论文值得关注，因为它解决了现有多智能体搜索系统在递归深度和动态协作上的关键瓶颈。对研究AI智能体、知识检索与复杂推理的开发者而言，其提出的过程经验重用和结构化委托思路具有很强的启发意义。

## 速览

WebSwarm是一种渐进递归委托框架，通过动态实例化搜索节点、耦合局部目标与搜索模式，实现任务分解、递归扩展与智能体协作。实验表明，在多种深广搜索基准上，WebSwarm显著优于单智能体和现有多智能体方法，有效解决了深度与覆盖度难以兼顾的问题。

## 关键点

- 提出WebSwarm框架，通过递归委托和协作机制同时提升搜索深度和广度
- 动态实例化搜索节点，每个节点可独立求解或进一步委托子节点
- 先探测网页信息组织结构，再指导节点扩展和过程级经验重用
- 在BrowseComp-Plus、WideSearch等基准上取得最佳性能

## 全文

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.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_ce8fdbfde4c93860659929e8