Discriminative World Models for Web Agents· 网络代理的世界模型
Recent web agents use world models for test-time action selection by sampling candidate actions, predicting the resulting web states, and ranking them with a ranker model or a Process Reward Model (PRM). These world models are typically trained via supervised next-state prediction to generate fixed representations like HTML or AXTree snapshots. However, this objective is misaligned with the downstream ranker, which relies on predicted states being discriminative across candidates to accurately score them. To address this, we introduce predicted-state matching, a training objective where the predicted representation must distinguish the true resulting state from those reached by alternative actions. We train these models using a branching web-agent dataset derived from WebArena Go-Browse tr
提出了网络代理世界模型新训练目标，提高状态辨识度。
- 核心方法
- 引入预测状态匹配训练目标，通过区分真实结果状态与备选动作达到的状态，提升模型的辨识能力。
- 适合谁读
- AI研究者 / 工程师
- 要解决的问题
- 现有的网络代理世界模型在训练时仅预测下一状态，不考虑状态的辨识度，导致测试时选择动作准确性不足。
- 关键实验
- 使用从WebArena Go-Browse派生的分支网络代理数据集进行了实验验证，但具体实验结果未提供。
- 主要贡献
- 新训练目标解决了状态表示的辨识度问题，提高了网络代理在复杂网页环境中的决策能力。
- 意义与局限
- 提高了网络代理在网页导航任务中的表现，但可能需要更多实验来验证其在其他任务中的泛化能力。