Web navigation requires agents to follow natural language goals, interact with web pages, and produce accurate answers. While recent advances leverage vision-language models and reinforcement learning, existing methods still suffer from single-step fragility due to reward misalignment and error propagation. To tackle the reward entanglement, we design Dynamic Dual-Policy Optimization (DDPO), which dynamically switches between a navigation-first mode for exploration and an answer-first mode for question-answering to mitigate reward conflict. To calibrate the single-step error, we propose Confidence-Guided Adaptive Navigation Reflection (CANR), a mechanism that estimates per-step confidence, triggers reflection only when necessary, and uses contrastive rewards to encourage self-correction to calibrate the single-step inaccuracy. With the above as the main components, we finally develop our StepGuard, a new framework of Guarding Web Navigation via Single-Step Calibration. Experiments demonstrate that our approach significantly improves navigation and answer accuracy, setting new state-of-the-art performance on standard web navigation benchmarks.

翻译：网页导航要求智能体遵循自然语言目标、与网页交互并生成准确答案。尽管近期进展借助了视觉语言模型和强化学习，现有方法仍因奖励错位与误差传播而存在单步脆弱性问题。为解决奖励纠缠，我们设计了动态双策略优化（DDPO），在探索阶段动态切换至导航优先模式，并在问答阶段切换至答案优先模式，以缓解奖励冲突。为校准单步误差，我们提出置信引导自适应导航反思机制（CANR），该机制可估算每步置信度、仅在必要时触发反思，并利用对比奖励鼓励自我修正，从而校准单步不准确性。以上述方法为核心组件，我们最终构建了StepGuard——一种通过单步校准实现网页导航防护的新框架。实验表明，我们的方法大幅提升了导航与答案准确率，在标准网页导航基准测试中刷新了最优性能记录。