Safe and Scalable Web Agent Learning via Recreated Websites

TL;DR

This paper introduces VeriEnv, a framework that creates safe, verifiable synthetic web environments from real websites, enabling scalable, self-evolving training for web agents without real-world risks.

Contribution

VeriEnv automatically clones real websites into executable environments, allowing agents to learn with verifiable rewards and scale training safely and efficiently.

Findings

Agents trained with VeriEnv generalize well to unseen websites.

Self-evolving training improves site-specific mastery.

Scaling environments enhances agent performance.

Abstract

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.