Paper Detail

ColorBrowserAgent: Complex Long-Horizon Browser Agent with Adaptive Knowledge Evolution

Jihong Wang, Jiamu Zhou, Weiming Zhang, Weiwen Liu, Zhuosheng Zhang, Xingyu Lou, Weinan Zhang, Huarong Deng, Jun Wang

arxiv Score 19.5

Published 2026-01-12 · First seen 2026-03-27

Research Track B · General AI

Abstract

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.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
now
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{wang2026colorbrowseragent,
  title = {ColorBrowserAgent: Complex Long-Horizon Browser Agent with Adaptive Knowledge Evolution},
  author = {Jihong Wang and Jiamu Zhou and Weiming Zhang and Weiwen Liu and Zhuosheng Zhang and Xingyu Lou and Weinan Zhang and Huarong Deng and Jun Wang},
  year = {2026},
  abstract = {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 kn},
  url = {https://arxiv.org/abs/2601.07262},
  keywords = {cs.HC},
  eprint = {2601.07262},
  archiveprefix = {arXiv},
}

Metadata

{}