WebSwarm: Recursive Multi-Agent Orchestration for Deep-and-Wide Web Search
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
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 57%gefsikatsinelou/MetaSearchMCP →
- PossiblePossibly related (embedding) · 57%redhat-community-ai-tools/UnifAI →
- PossiblePossibly related (embedding) · 52%felladrin/MiniSearch →
- PossiblePossibly related (embedding) · 52%ahumblenerd/tour-of-agents →
- PossiblePossibly related (embedding) · 27%deepset-ai/haystack →
“Possibly related via embedding similarity 0.59 (not asserted). Timestamp check: artifact slightly before paper (-7d).”
- PossiblePossibly related (embedding) · 31%neuml/txtai →
“Possibly related via embedding similarity 0.61 (not asserted). Timestamp check: artifact after paper (+4d).”
- FuzzySimilar title/name (fuzzy) · 59%AgentCore-8B →
“Fuzzy title match (0.73): “WebSwarm: Recursive Multi-Agent Orchestration for Deep-and-W” ≈ “AgentCore-8B””
- LinkedLinked via arxiv author · 85%Xiaoshuai Song →
“WebSwarm: Recursive Multi-Agent Orchestration for Deep-and-Wide Web Search”