让网页智能体主动在关键步骤调用经验，提升任务完成率。
ExpSeek: Self-Triggered Experience Seeking for Web Agents
- 根据模型内部信号自动判断何时调用经验
- 在四个基准上使大模型任务成功率提升7.5%~9.3%
- 小经验模型也能显著提升大模型表现，适合需要自适应的智能体
网页智能体中的经验干预成为一种有前景的技术范式，通过积累的经验提升交互能力。然而，现有方法多在任务执行前被动注入全局经验，难以适应交互过程中动态变化的上下文。我们提出ExpSeek，将经验引入方式改为步骤级主动寻求：(1) 利用模型内在信号估算步骤级熵阈值，决定干预时机；(2) 设计步骤级定制的经验内容。在Qwen3-8B和32B模型上，跨四个具有挑战性的网页智能体基准测试表明，ExpSeek分别实现9.3%和7.5%的绝对性能提升。实验验证了熵作为自触发信号的可行性与优势，揭示即使仅使用4B规模的经验模型，也能显著提升更大规模代理模型的表现。代码已开源：https://github.com/WYRipple/ExpSeek。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。