用AI克隆网站，让网页智能体安全高效自进化训练
Safe and Scalable Web Agent Learning via Recreated Websites
- 用语言模型自动创建可执行的仿真网站环境
- 训练后在未见网站上表现更好，且能自主提升技能
- 适合研究智能体训练、自动化测试与安全实验的开发者
训练自主网页智能体受限于真实网站：它们不安全、难以重置，且很少提供可验证的反馈。我们提出VeriEnv框架，利用语言模型作为环境创造者，将真实网站自动克隆为完全可执行、可验证的合成环境。通过提供基于Python SDK的受控内部访问，VeriEnv使智能体能够自动生成任务，并获得确定性、程序化可验证的奖励，不再依赖启发式或大模型判断。该设计将智能体学习与不安全的真实交互解耦，同时支持通过环境扩展实现规模化自演化。在网页智能体基准测试中，使用VeriEnv训练的智能体展现出对未知网站的泛化能力，通过自我演进训练达成特定网站精通，并受益于训练环境数量的增加。代码与资源将在接受后发布于https://github.com/kyle8581/VeriEnv。
原文摘要 · Abstract (English)
Training autonomous web agents is fundamentally limited by the environments they learn from: real-world websites are unsafe to explore, hard to reset, and rarely provide verifiable feedback. We propose VeriEnv, a framework that treats language models as environment creators, automatically cloning real-world websites into fully executable, verifiable synthetic environments. By exposing controlled internal access via a Python SDK, VeriEnv enables agents to self-generate tasks with deterministic, programmatically verifiable rewards, eliminating reliance on heuristic or LLM-based judges. This design decouples agent learning from unsafe real-world interaction while enabling scalable self-evolution through environment expansion. Through experiments on web agent benchmarks, we show that agents trained with VeriEnv generalize to unseen websites, achieve site-specific mastery through self-evolving training, and benefit from scaling the number of training environments. Code and resources will be released at https://github.com/kyle8581/VeriEnv upon acceptance.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。