SynWeaver：面向Web智能体的网站先验任务与轨迹协同合成
SynWeaver: Website-Prior Task and Trajectory Co-Synthesis for Web Agents
查看机构详情
- Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
SynWeaver是面向Web智能体的协同合成框架，通过构建网站地图并训练带网站先验的UI感知模型，生成任务与轨迹，在WebArena等数据集上优于基线，提升了泛化能力。
中文摘要 AI 辅助
Web智能体因缺乏网站特定监督，往往难以泛化到未见过的网站。近期基于探索的数据合成方法减少了人工标注，但仍面临两个关键局限：它们往往无法覆盖网站的全部功能，且在缺乏足够网站先验知识的情况下，容易提出虚构的任务，进而限制了下游轨迹合成的多样性与效率。我们提出SynWeaver，这是一个旨在应对上述挑战的网站先验任务-轨迹协同合成框架。SynWeaver首先开展结构化网站探索，构建覆盖目标网站大量功能不同的页面状态与可执行交互的网站地图；随后从该地图中推导页面级与过渡级监督，以训练具有网站特定先验的UI感知模型，从而实现更贴合实际的任务提议；最后，SynWeaver执行协同任务-轨迹合成，当任务与执行轨迹不一致时对二者进行联合更新，再对收集到的结果进行验证与修复，以生成可执行、语义对齐的监督信号。在WebArena与WebVoyager上的实验表明，SynWeaver始终优于强大的合成基线方法，能为域内和域外泛化提供更有效的监督。
英文摘要
Web agents often struggle to generalize to unseen websites because they lack website-specific supervision. Recent exploration-based data synthesis methods reduce manual annotation, but they still face two key limitations: they often fail to cover the full functionality of a website, and without sufficient website prior knowledge, they tend to propose hallucinated tasks, which in turn limits the diversity and efficiency of downstream trajectory synthesis. We present \textbf{SynWeaver}, a website-prior task-trajectory co-synthesis framework designed to address these challenges. SynWeaver first performs structured website exploration and constructs a website map that covers a broad set of functionally distinct page states and executable interactions on the target website. It then derives page-level and transition-level supervision from this map to train a UI-aware model with website-specific priors, enabling more grounded task proposals. Finally, SynWeaver performs collaborative task-trajectory synthesis, jointly updating the task and execution trajectory when they become inconsistent, and then verifies and repairs the collected results to produce executable, semantically aligned supervision. Experiments on WebArena and WebVoyager demonstrate that SynWeaver consistently outperforms strong synthesis baselines and yields more effective supervision for both in-domain and out-of-domain generalization.
