WebSwarm is a progressive recursive delegation framework designed to address the limitations of single ReAct-style agents in handling complex, deep-and-wide web search tasks. It dynamically instantiates agentic search nodes that couple local objectives with specific search modes, allowing them to either solve tasks directly or delegate to child nodes.
- The system jointly constructs task decomposition, recursive expansion, and agent collaboration during inference.
- Nodes return evidence and results upward, enabling parent nodes to expand, revise, or aggregate the search process.
- WebSwarm probes web organization to ground node expansion and reuses process-level experience across homogeneous sibling nodes.
- Experiments on BrowseComp-Plus, WideSearch, DeepWideSearch, and GISA show consistent outperformance over single-agent and multi-agent baselines.