ColorBrowserAgent: Complex Long-Horizon Browser Agent with Adaptive Knowledge Evolution
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913057249165312 |
|---|---|
| author | Wang, Jihong Zhou, Jiamu Zhang, Weiming Wang, Teng Liu, Weiwen Zhang, Zhuosheng Lou, Xingyu Zhang, Weinan Deng, Huarong Wang, Jun |
| author_facet | Wang, Jihong Zhou, Jiamu Zhang, Weiming Wang, Teng Liu, Weiwen Zhang, Zhuosheng Lou, Xingyu Zhang, Weinan Deng, Huarong Wang, Jun |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_07262 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ColorBrowserAgent: Complex Long-Horizon Browser Agent with Adaptive Knowledge Evolution Wang, Jihong Zhou, Jiamu Zhang, Weiming Wang, Teng Liu, Weiwen Zhang, Zhuosheng Lou, Xingyu Zhang, Weinan Deng, Huarong Wang, Jun Human-Computer Interaction 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. |
| title | ColorBrowserAgent: Complex Long-Horizon Browser Agent with Adaptive Knowledge Evolution |
| topic | Human-Computer Interaction |
| url | https://arxiv.org/abs/2601.07262 |