Experience intervention in web agents emerges as a promising technical paradigm, enhancing agent interaction capabilities by providing valuable insights from accumulated experiences. However, existing methods predominantly inject experience passively as global context before task execution, struggling to adapt to dynamically changing contextual observations during agent-environment interaction. We propose ExpSeek, which shifts experience toward step-level proactive seeking: (1) estimating step-level entropy thresholds to determine intervention timing using the model's intrinsic signals; (2) designing step-level tailored experience content. Experiments on Qwen3-8B and 32B models across four challenging web agent benchmarks demonstrate that ExpSeek achieves absolute improvements of 9.3% and 7.5%, respectively. Our experiments validate the feasibility and advantages of entropy as a self-triggering signal, reveal that even a small-scale 4B experience model can significantly boost the performance of larger agent models. The code is released at https://github.com/WYRipple/ExpSeek.
@article{arxiv.2601.08605,
title = {ExpSeek: Self-Triggered Experience Seeking for Web Agents},
author = {Wenyuan Zhang and Xinghua Zhang and Haiyang Yu and Shuaiyi Nie and Bingli Wu and Juwei Yue and Tingwen Liu and Yongbin Li},
journal= {arXiv preprint arXiv:2601.08605},
year = {2026}
}
Comments
ACL 2026 Findings, the code is accessible at https://github.com/WYRipple/ExpSeek