AI 开始自己进化自己了
现在的 AI 系统，部署之后大多就“定型”了：任务固定、反馈固定，它只能在框里自我改进。这篇综述讲的是让 AI 自己进化自己——不是单个 AI 变强，而是多个 AI 互相施加压力、一起变强，连任务和环境都跟着变，最后连“进化机制”本身都能进化。研究者把这种“共进化”分成三个阶段：AI 之间互相适应(对抗、合作、组织)、AI 和环境互相改变、再到进化机制本身可进化。它不是你明天能用上的东西，但它指向一个方向：AI 不再只是被人类设计出来的工具，而是能自己走出人类没画过的路。
📄 原文摘要(英文)
Agentic systems are increasingly expected to improve after deployment, yet single-entity self-evolution is often bounded by a static learning context, such as fixed tasks and feedback. This survey focuses on co-evolution in agentic systems, a multi-component form of self-evolution in which multiple agents and their environment impose adaptive pressure on one another. To organize existing papers, we propose a progressive three-stage taxonomy that traces how the system gradually sheds human-engineered constraints. Agent--Agent Co-Evolution studies how agents adapt through dynamic peers, including adversarial, collaborative, and organizational adaptation. Agent--Environment Co-Evolution extends this loop to adaptive tasks, feedback, and interaction spaces that change with the agents. Meta Co-Evolution further explores the possibility of making the evolution mechanism itself evolvable. We also discuss open challenges in evaluating such systems, scaling them across multiple components, and keeping increasingly autonomous evolutionary processes safe and controllable. This survey provides a unified foundation for building robust and open-ended agentic systems that can improve beyond fixed human-designed paths.