智能体系统蒸馏：跨模型、工件与执行框架的路线图
Distilling Agentic Systems: A Roadmap across Models, Artifacts, and Harnesses
- Central South University（中南大学）
- Beijing Academy of Artificial Intelligence（北京人工智能研究院）
- Hong Kong Polytechnic University（香港理工大学）
- Beijing University of Posts and Telecommunications（北京邮电大学）
- University of Illinois at Chicago（伊利诺伊大学芝加哥分校）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出智能体蒸馏概念，系统梳理知识在模型、工件、执行框架及基质中的迁移路径，并建立评估框架，为复杂智能体系统的可靠开发奠定基础。
AI中文摘要：
现代智能体越来越依赖记忆、工具和执行逻辑，因此其能力已超越模型参数本身。这一转变暴露了传统知识蒸馏的局限性，传统蒸馏关注学生模型如何模仿教师模型。我们将智能体蒸馏定义为将任务解决知识从教师智能体持续迁移到学生智能体的过程。我们的研究通过迁移知识在何处保留来组织该领域：在模型内部、作为工件、通过执行框架，或跨底层基质。这一视角将迁移证据与其结果分离，并阐明知识如何在智能体组件之间流动。我们开发了一个评估框架，将知识保留与因果贡献和部署效用相关联。这些贡献共同为日益复杂的智能体系统的可靠、可维护和安全开发奠定了基础。
英文摘要：
Modern agents increasingly rely on memories, tools, and execution logic, so their competence extends beyond model parameters. This shift exposes a limitation of conventional knowledge distillation, which asks how a student model imitates a teacher model. We define Agent Distillation as the persistent transfer of task-solving knowledge from a teacher agent to a student agent. Our study organizes the field by where transferred knowledge is retained: within the model, as artifacts, through the execution harness, or across substrates. This perspective separates transfer evidence from its outcome and clarifies how knowledge moves between agent components. We develop an evaluation framework that relates retention to causal contribution and deployed utility. Together, these contributions establish a foundation for the reliable, maintainable, and safe development of increasingly complex agentic systems.
