Environment Scaling For Interactive Agentic Experience Collection: A Survey

Abstract

LLM-based agents can autonomously accomplish complex tasks across various domains. However, to further cultivate capabilities such as adaptive behavior and long-term decision-making, training on static datasets built from human-level knowledge is insufficient. These datasets are costly to construct and lack both dynamism and realism. A growing consensus is that agents should instead interact directly with environments and learn from experience through reinforcement learning. We formalize this iterative process as the Generation-Execution-Feedback (GEF) loop, where environments generate tasks to challenge agents, return observations in response to agents' actions during task execution, and provide evaluative feedback on rollouts for subsequent learning. Under this paradigm, environments function as indispensable producers of experiential data, highlighting the need to scale them toward greater complexity, realism, and interactivity. In this survey, we systematically review representativ

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyhuang2025environment

Related papers

• Towards Agentic Self-learning Llms In Search Environment (2025)0.00
• Autoenv: Automated Environments For Measuring Cross-environment Agent Learning (2025)0.00
• Open-ended Learning Leads To Generally Capable Agents (2021)0.00
• A Survey On Enhancing Reinforcement Learning In Complex Environments: Insights From Human And LLM Feedback (2024)0.00
• External Model Motivated Agents: Reinforcement Learning For Enhanced Environment Sampling (2024)0.00
• Agentevolver: Towards Efficient Self-evolving Agent System (2025)0.00
• Agent-pro: Learning To Evolve Via Policy-level Reflection And Optimization (2024)9.59
• Investigating Enactive Learning For Autonomous Intelligent Agents (2018)0.00