梳理自进化智能体如何自主优化，从经验中积累能力。
Self-Improvements in Modern Agentic Systems: A Survey
- 将智能体视为基础模型与提示、记忆等组件的组合系统
- 提出自更新算子机制，实现参数或结构的自我调整
- 适合研究智能体演化、自主系统设计的学者参考
自进化自主智能体正从研究原型走向实际部署。核心目标是实现可控演化或适应，仅依赖经验而无需或极少人工干预。本综述将现代自进化智能体定义为可适应系统，能将经验转化为累积的能力提升。我们提出一个系统级框架，将智能体建模为基础模型与提示、记忆、工具及控制逻辑构成的操作支撑结构的组合。在此框架下，自进化被形式化为一种由自身触发的更新算子，用于获取并提交对模型参数或支撑组件的修改。我们按更新目标和驱动信号对已有工作进行分类，回顾应用案例，讨论评估方法，并指出开放问题与未来方向。技术更新可关注 https://github.com/selfimproving-agent/awesome-Self-Improving-Agents。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。