Environments serve as interactive systems for large language model (LLM) based agents across diverse scenarios and play a crucial role in driving the continual evolution of model capabilities. Despite this importance, existing work lacks a systematic categorization and deep analysis. This paper systematically studies current researches on agentic environments from the perspective of the environment engineering lifecycle, covering their modeling, synthesis, evaluation and application. Specifically, the paper first introduces representative environments from the perspectives of eight attributes and eight domains, providing detailed analyses of their development paths and highlighting their core capabilities. Second, for automated environment synthesis, two paradigms are introduced, such as symbolic synthesis and neural synthesis. This paper also shows different environment evaluation methods in each paradigm. Thirdly, the corresponding environment applications from the perspective of agent-environment co-evolution are discussed. In specific, the paper characterizes the primary pathways for agent evolution in dynamic environments from four complementary perspectives: memory-centric experience evolution, orchestration-centric workflow evolution, trajectory-centric offline evolution, and exploration-centric online evolution. And three paradigms of environment evolution are identified, namely neural-driven, difficulty-driven, and scaling-driven approaches. At last, several promising future directions are discussed, including Environment-as-a-Service, Multi-agent Environments, and Neural-Symbolic Environments.

翻译：环境作为基于大型语言模型的智能体在多样化场景下的交互系统，在推动模型能力持续演进中发挥着关键作用。尽管其重要性不言而喻，但现有研究缺乏系统性的分类与深入分析。本文从环境工程生命周期的视角系统梳理了当前关于智能体环境的研究，涵盖其建模、合成、评估与应用。具体而言，本文首先从八个属性与八个领域维度介绍了代表性环境，详细分析了其发展路径并突出核心能力。其次，针对自动化环境合成，引入了符号合成与神经合成两种范式，并展示了各范式下的不同环境评估方法。再次，从智能体-环境协同演化的视角探讨了相应的环境应用。具体而言，本文从四个互补维度刻画了动态环境中智能体演化的主要路径：以记忆为中心的体验演化、以编排为中心的工作流演化、以轨迹为中心的离线演化、以及以探索为中心的在线演化；同时识别出环境演化的三种范式，即神经驱动、难度驱动与规模驱动方法。最后，讨论了包括环境即服务、多智能体环境、神经符号环境在内的若干有前景的未来方向。