让网页代理学会预判风险，自动修正错误操作。
World-Model-Augmented Web Agents with Action Correction
- 用世界模型辅助决策，提升动作合理性。
- 模拟执行后果，发现风险并触发修正，准确率提升1.8%。
- 适合需要高可靠性的自动化网页任务场景。
基于大语言模型的网页代理在自动化网页任务方面展现出巨大潜力。然而，现有代理受限于对环境变化的预测能力，缺乏对执行风险的全面认知，可能过早采取高风险动作导致失败。为此，我们提出WAC，通过模型协作、后果模拟和反馈驱动的动作优化来解决该问题。引入多代理协作机制，使动作模型可向世界模型（作为网页环境专家）咨询策略建议，并结合环境状态转移先验知识生成可执行动作。为实现风险感知的鲁棒执行，设计两阶段推理链：由专注于环境状态转移的世界模型模拟动作结果，再由裁判模型审查，必要时触发动作修正反馈。实验表明，WAC在VisualWebArena上绝对提升1.8%，在Online-Mind2Web上提升1.3%。
原文摘要 · Abstract (English)
Web agents based on large language models have demonstrated promising capability in automating web tasks. However, current web agents struggle to reason out sensible actions due to the limitations of predicting environment changes, and might not possess comprehensive awareness of execution risks, prematurely performing risky actions that cause losses and lead to task failure. To address these challenges, we propose WAC, a web agent that integrates model collaboration, consequence simulation, and feedback-driven action refinement. To overcome the cognitive isolation of individual models, we introduce a multi-agent collaboration process that enables an action model to consult a world model as a web-environment expert for strategic guidance; the action model then grounds these suggestions into executable actions, leveraging prior knowledge of environmental state transition dynamics to enhance candidate action proposal. To achieve risk-aware resilient task execution, we introduce a two-stage deduction chain. A world model, specialized in environmental state transitions, simulates action outcomes, which a judge model then scrutinizes to trigger action corrective feedback when necessary. Experiments show that WAC achieves absolute gains of 1.8% on VisualWebArena and 1.3% on Online-Mind2Web.
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。