arXiv:2606.12191v1 Announce Type: new 
Abstract: 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.

استعرضت دراسة حديثة بعنوان 'هندسة البيئات الوكيلة لنماذج اللغة الكبيرة' دورة حياة نمذجة البيئة، والتوليف، والتقييم، والتطبيق للبيئات الخاصة بالوكلاء المعتمدين على نماذج اللغة الكبيرة (LLM). تبرز الدراسة أهمية البيئات التفاعلية في تعزيز قدرات نماذج اللغة الكبيرة، مقدمةً تحليلاً مفصلاً لمجموعة متنوعة من البيئات التمثيلية عبر ثمانية سمات ومجالات.

Una reciente encuesta titulada 'Ingeniería de Entornos Agénticos para Modelos de Lenguaje de Gran Tamaño' examina sistemáticamente el ciclo de vida de la modelización, síntesis, evaluación y aplicación de entornos para agentes basados en modelos de lenguaje de gran tamaño (LLM). El estudio destaca la importancia de los entornos interactivos para mejorar las capacidades de los LLM, proporcionando un análisis detallado de varios entornos representativos a través de ocho atributos y dominios.

Une récente enquête intitulée 'Ingénierie des Environnements Agentiques pour les Modèles de Langage de Grande Taille' examine systématiquement le cycle de vie de la modélisation, de la synthèse, de l'évaluation et de l'application des environnements pour les agents basés sur des modèles de langage de grande taille (LLM). L'étude souligne l'importance des environnements interactifs pour améliorer les capacités des LLM, en fournissant une analyse détaillée de divers environnements représentatifs à travers huit attributs et domaines.

A recent survey titled 'Agentic Environment Engineering for Large Language Models' systematically examines the lifecycle of environment modeling, synthesis, evaluation, and application for large language model (LLM) agents. The study highlights the importance of interactive environments in enhancing LLM capabilities, providing a detailed analysis of various representative environments across eight attributes and domains.