TimeWarp: Evaluating Web Agents by Revisiting the Past
AI 摘要
论文提出TimeWarp基准评估Web Agent在Web演变下的泛化能力,并提出TimeTraj算法提升Agent鲁棒性。
主要贡献
- 提出TimeWarp基准,模拟Web演变环境
- 发现现有Web Agent在Web变化下的脆弱性
- 提出TimeTraj算法,利用多版本数据提升Agent性能
方法论
构建包含不同UI版本的Web环境,使用行为克隆训练Agent,并提出Plan Distillation方法收集多版本轨迹。
原文摘要
The improvement of web agents on current benchmarks raises the question: Do today's agents perform just as well when the web changes? We introduce TimeWarp, a benchmark that emulates the evolving web using containerized environments that vary in UI, design, and layout. TimeWarp consists of three web environments, each with six UI versions spanning different eras of the internet, paired with a set of complex, realistic tasks requiring different forms of web navigation. Our experiments reveal web agents' vulnerability to changes and the limitations of behavior cloning (BC) on single-version trajectories. To address this, we propose TimeTraj, a simple yet effective algorithm that uses plan distillation to collect trajectories across multiple versions. By training agents on teacher rollouts using our BC-variant, we achieve substantial performance gains: $20.4\%\rightarrow37.7\%$ for Qwen-3 4B and $0\%\rightarrow27.0\%$ for Llama-3.1 8B models. We hope our work helps researchers study generalization across web designs and unlock a new paradigm for collecting plans rather than trajectories, thereby improving the robustness of web agents.