发表机构
School of Artificial Intelligence, Jilin University; King Abdullah University of Science and Technology (KAUST); University of Alberta; The Swiss AI Lab IDSIA/USI/SUPSI（吉林大学人工智能学院; 阿卜杜拉国王科技大学; 阿尔伯塔大学; 瑞士人工智能实验室IDSIA/USI/SUPSI）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
综述现代自我改进智能体从研究走向部署，目标是经验驱动的可控进化。提出系统级框架，将智能体视为基础模型与操作支架的耦合配置，自我改进形式化为更新算子，还组织回顾了相关工作、应用、评估等内容并展望未来。
AI 中文摘要
自我改进的自主智能体正从研究原型走向实际部署系统。主要目标是通过最少甚至无需人类输入的经验实现可控的进化或适应。本综述将现代自我改进智能体视为将经验转化为累积能力提升的自适应系统。我们提供了一个系统级框架，将现代智能体表示为基础模型与提示、记忆、工具和控制逻辑操作支架相耦合的配置。在此框架内，自我改进被形式化为一个自我诱导更新算子，用于获取并提交对模型参数或支架组件的更新。我们按更新目标和驱动变化的信号对先前工作进行组织，然后回顾应用并讨论评估，最后列出开放问题和未来方向。为方便起见，我们在这个https网址跟踪技术更新。
英文摘要
Self-improving autonomous agents are moving from research prototypes to deployed systems. The primary goal is controllable evolution, or adaptation, from experience with minimal or even no human input. This survey frames modern self-improving agents as adaptive systems that convert experience into accumulated capability gains. We offer a system-level framework that represents a modern agent as a configuration coupling a foundation model with an operational scaffold of prompts, memory, tools, and control logic. Within this framework, self-improvement is formalized as a self-induced update operator that obtains and commits updates to model parameters or scaffold components. We organize prior work by update target and by the signals that drive change, then review applications and discuss evaluation, before closing with open problems and future directions. For convenience, we track technical updates on https://github.com/selfimproving-agent/awesome-Self-Improving-Agents.
Comments97 pages, 12 figures. Project page: https://selfimproving-agent.github.io/ Repository: https://github.com/selfimproving-agent/awesome-Self-Improving-Agents
