做智能体编排的团队终于有了低成本替代方案——把工作流写进模型权重而非上下文，成本降两个数量级，质量不掉。做客服、保险、旅行预订自动化的开发者可以直接看论文里的14节点和55节点案例。
当前智能体编排框架（如LangGraph、CrewAI等）已超过29万GitHub星标，但都依赖外部编排器，每次交互都需注入指令和路由决策，消耗上下文窗口且依赖前沿模型。最新研究提出将工作流直接编译进小模型权重，创建“地下智能体”，在旅行预订、Zoom支持、保险理赔三个任务上，以不到前沿模型1%的成本达到接近前沿模型的质量。该方法解决了程序化任务中编排架构的三大痛点：上下文窗口消耗、必须使用前沿模型、专有流程暴露给第三方。研究团队通过实证表明，小模型微调后能完全内化复杂工作流，无需外部编排。
Compiling Agentic Workflows into LLM Weights: Near-Frontier Quality at Two Orders of Magnitude Less Cost
Agent orchestration frameworks have proliferated, collectively exceeding 290,000 GitHub stars across LangGraph, CrewAI, Google ADK, OpenAI Agents SDK, Semantic Kernel, Strands, and LlamaIndex. All follow the same pattern: an external orchestrator above the LLM, injecting instructions and routing decisions every turn. Recent work has shown this architecture is dominated for procedural tasks by simply providing the procedure in a frontier model's system prompt [Dennis et al., 2026a], at the cost of consuming the context window, requiring a frontier model for every conversation, and exposing proprietary procedures to third-party providers. Compiling the procedure into the weights of a small fine-tuned model -- creating a subterranean agent -- should resolve all of these concerns, and prior work (SimpleTOD, FireAct, SynTOD, WorkflowLLM, Agent Lumos) has shown the technique works. Yet developer adoption has overwhelmingly favored orchestration. We identify three perceived barriers and address each empirically across travel booking (14 nodes), Zoom support (14 nodes, product-specific knowledge), and insurance claims (55 nodes, 6 decision hubs).