With the advancement of vision-language models, web automation has made significant progress. However, deploying autonomous agents in real-world settings remains challenging, primarily due to site heterogeneity, where generalist models lack domain-specific priors for diverse interfaces, and long-horizon instability, characterized by the accumulation of decision drift over extended interactions. To address these challenges, we introduce ColorBrowserAgent (Complex Long-Horizon Browser Agent), a knowledge-evolving agent for robust web automation. Our approach addresses these challenges through two synergistic mechanisms: human-in-the-loop knowledge adaptation that transforms sparse human feedback into reusable domain knowledge, and knowledge-aligned progressive summarization that stabilizes long interactions through memory compression. Extensive experiments on WebArena, WebChoreArena and industrial deployment show that ColorBrowserAgent consistently outperforms strong baselines. It achieves a state-of-the-art success rate of 71.2% on WebArena and maintains 47.4% performance under zero-shot transfer setting on WebChoreArena. In commercial deployment, it improves user satisfaction by 19.3% relatively, verifying its robustness in real-world scenarios.

翻译：随着视觉语言模型的发展，网络自动化已取得显著进展。然而，在真实世界场景中部署自主智能体仍然面临挑战，这主要源于两方面：站点异质性，即通用模型缺乏针对多样化界面的领域先验知识；以及长程不稳定性，其特点是决策漂移在长时间交互过程中的累积。为应对这些挑战，我们提出了ColorBrowserAgent（复杂长程浏览器智能体），一种用于鲁棒网络自动化的知识演化智能体。我们的方法通过两种协同机制解决这些挑战：人机协同知识适应，将稀疏的人类反馈转化为可复用的领域知识；以及知识对齐的渐进式摘要，通过记忆压缩来稳定长程交互。在WebArena、WebChoreArena以及工业部署上进行的大量实验表明，ColorBrowserAgent始终优于强基线模型。它在WebArena上实现了71.2%的最新成功率，并在WebChoreArena的零样本迁移设置下保持了47.4%的性能。在商业部署中，它相对提升了19.3%的用户满意度，验证了其在真实场景中的鲁棒性。