AI 协作不再靠死板剧本，主智能体现场写流程
现在的多智能体系统，分工是提前写死的：谁先做、谁后做、谁听谁的，都是固定剧本。碰到没见过的任务，这套班子就僵住了。DynaFlow 换了个思路：让主智能体自己决定要不要叫帮手，并且现场写一段可执行的程序来调度子智能体——可以串行、可以并行、可以互相传信息、还能验证结果。而且它只训练主智能体，子智能体全部冻结，把「怎么调度」和「单个能力」彻底分开。在数学推理、科学问答、多跳检索六个基准上，它比同底座的强基线高出 10.9 个百分点。这不是你明天能用的产品，但它指向一个趋势：AI 团队协作正在从「固定编制」走向「现场组队」。
📄 原文摘要(英文)
Multi-agent systems often rely on predefined collaboration structures, limiting their ability to adapt to diverse task requirements. We introduce DynaFlow, a framework that integrates free-form executable workflow synthesis into the action space of the main agent. The agent decides when collaboration is needed and generates task-specific programs that coordinate sub-agents through sequential or parallel execution, structured information exchange, and verification. Execution results and traces inform subsequent actions, enabling the agent to adapt collaboration as reasoning progresses. We train only the main agent through supervised fine-tuning on distilled trajectories, followed by refinement on examples filtered for unsupported premises, biased verification, and information-flow defects. All sub-agents remain fixed, separating orchestration learning from executor capability improvement. Across six benchmarks spanning mathematical reasoning, scientific question answering, and multi-hop retrieval, DynaFlow achieves 88.08% overall accuracy in Forced mode, outperforming the strongest evaluated baseline by 10.90 percentage points with the same Qwen3.5-27B backbone. Workflow analysis finds more explicit use, verification, and refinement of upstream outputs after training, highlighting cross-stage information flow as a key dimension of multi-agent orchestration.