发表机构
Hong Kong University of Science and Technology; University of Illinois Urbana-Champaign; The Chinese University of Hong Kong; The University of Hong Kong; Peking University（香港科技大学; 伊利诺伊大学厄巴纳-香槟分校; 香港中文大学; 香港大学; 北京大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本综述聚焦智能体系统的协同进化，提出三阶段分类法梳理其发展，探讨相关开放挑战，为构建超越人类设计路径的自主智能体系统提供统一基础。
AI 中文摘要
智能体系统在部署后愈发需要实现性能提升，但单一实体的自主进化常受限于静态学习语境，如固定任务与反馈。本综述聚焦智能体系统中的协同进化，这是一种多组件形式的自主进化，其中多个智能体与其环境相互施加适应性压力。为梳理现有文献，本文提出渐进式三阶段分类法，追踪系统逐步摆脱人类设计约束的过程：智能体-智能体协同进化研究智能体如何通过动态同伴实现适应，包括对抗性、协作性与组织性适应；智能体-环境协同进化将该循环扩展至随智能体变化的适应性任务、反馈与交互空间；元协同进化则进一步探索让进化机制本身可进化的可能性。本文还讨论了此类系统评估、跨多组件扩展，以及保障日益自主的进化过程安全可控等开放挑战，为构建能超越固定人类设计路径实现性能提升的鲁棒、开放式智能体系统提供统一基础。
英文摘要
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.
