做长时深度研究或复杂任务自动化的开发者，终于有了一个能高效委托子任务的模型——SearchSwarm 用30B参数就超越了更大模型，值得直接试试它的开源实现。
SearchSwarm 提出了一种新范式，让主智能体通过分解任务并委托给子智能体来应对无限增长的上下文需求，从而解决长时深度研究任务。该团队设计了一个引导框架，生成高质量的任务分解和委托轨迹，并用这些数据微调模型，将委托智能内化到模型权重中。SearchSwarm-30B-A3B 在 BrowseComp 和 BrowseComp-ZH 上分别取得 68.1 和 73.3 的成绩，是同等规模模型中的最佳结果。这项工作填补了开源社区在委托智能训练数据合成方面的空白，并计划开源相关资源。
SearchSwarm: Towards Delegation Intelligence in Agentic LLMs for Long-Horizon Deep Research
Large language models are increasingly expected to handle complex, long-horizon real-world tasks whose context demands can grow without bound, yet model context windows remain inherently finite. Recent work explores a paradigm where a main agent decomposes tasks and dispatches subtasks to subagents, which execute and return only summarized results, conserving the main agent's context budget. However, performing this well requires delegation intelligence: the ability to decompose complex tasks, determine when and what to delegate, and integrate returned results into the ongoing workflow. Training data for this capability is scarce in naturally occurring text, and to our knowledge, how to synthesize such data and train models to acquire this capability remains largely unexplored in the open-source community. To bridge this gap, we present a preliminary exploration targeting deep research, a representative long-horizon agent task. Specifically, we design a harness that guides the model toward high-quality task decomposition and delegation, while constraining subagents to return results properly to support the main agent's workflow. The harness-guided trajectories naturally encode correct delegation decisions, which we use as supervised fine-tuning data to internalize delegation intelligence into model weights. Our resulting model, SearchSwarm-30B-A3B, achieves 68.1 on BrowseComp and 73.3 on BrowseComp-ZH, the best results among all models of comparable scale. We will release our harness, model weights, and training data to facilitate future research.