Autoenv: Automated Environments For Measuring Cross-environment Agent Learning

Abstract

Humans naturally adapt to diverse environments by learning underlying rules across worlds with different dynamics, observations, and reward structures. In contrast, existing agents typically demonstrate improvements via self-evolving within a single domain, implicitly assuming a fixed environment distribution. Cross-environment learning has remained largely unmeasured: there is no standard collection of controllable, heterogeneous environments, nor a unified way to represent how agents learn. We address these gaps in two steps. First, we propose AutoEnv, an automated framework that treats environments as factorizable distributions over transitions, observations, and rewards, enabling low-cost (4.12 USD on average) generation of heterogeneous worlds. Using AutoEnv, we construct AutoEnv-36, a dataset of 36 environments with 358 validated levels, on which seven language models achieve 12-49% normalized reward, demonstrating the challenge of AutoEnv-36. Second, we formalize agent learning

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyzhang2025autoenv

Related papers

• Environment Scaling For Interactive Agentic Experience Collection: A Survey (2025)0.00
• MAESTRO: Open-ended Environment Design For Multi-agent Reinforcement Learning (2023)0.00
• An Efficient Open World Environment For Multi-agent Social Learning (2025)0.00
• Open-ended Learning Leads To Generally Capable Agents (2021)0.00
• Extending Environments To Measure Self-reflection In Reinforcement Learning (2021)0.00
• Discovering Minimal Reinforcement Learning Environments (2024)0.00
• Improving Generalization To New Environments And Removing Catastrophic Forgetting In Reinforcement Learning By Using An Eco-system Of Agents (2022)0.00
• Investigating Enactive Learning For Autonomous Intelligent Agents (2018)0.00