SearchSwarm: Delegation Intelligence for LLM Agents in Long-Horizon Deep Research
SearchSwarm (arXiv:2606.09730) introduces a multi-agent framework where a main LLM decomposes long research tasks and dispatches subtasks to specialized subagents that return only summarized results to fit the main context window. Training data is synthesized via a harness guiding high-quality decomposition. SearchSwarm-30B-A3B achieves 68.1 on BrowseComp and 73.3 on BrowseComp-ZH — best results among comparable-scale open models. Weights, training data, and harness are being released open-source.
Why it matters
Context-window saturation is a practical ceiling for LLM-based research agents. SearchSwarm targets this with a trainable delegation strategy rather than a heuristic one, and the open-source release enables reproducible follow-up work.
Importance: 2/5
Solid open-source multi-agent research paper; SOTA on BrowseComp for open models; delegation as a trainable skill is a useful framing.