让网页搜索更懂专业领域，精准找信息
WebExpert: domain-aware web agents with critic-guided expert experience for high-precision search
- 用领域知识动态提取关键信息点，自动归纳主题和规则
- 在金融、医药等专业场景中，准确率提升1.5至3.6个百分点
- 适合需要高精度网页搜索的科研、医疗、金融从业者
金融、生物医学和制药等领域的专业网络任务仍面临挑战，因缺乏领域先验：查询易漂移，证据噪声大，推理易出错。我们提出WebExpert，一种端到端实现的领域感知网页代理，包含：(i) 基于句子级经验检索与主题合并、规则提炼；(ii) 基于弱监督的轻量级维度自举，从数据中自动学习时间、地区、政策、行业等维度，替代人工编写词典；(iii) 通过成对偏好学习与覆盖感知目标，联合优化查询规划与检索。推理时，轻量级经验门控机制在高置信度下引导解码聚焦活跃维度，低置信度时自动回退。在GAIA、GPQA、HLE和WebWalkerQA上，相比最强浏览基线，答案精确匹配（EM）提升1.5–3.6个百分点，同时减少页面跳转次数。分析显示，在检索、主题合并、维度诱导和偏好训练方面均有稳定增益。
原文摘要 · Abstract (English)
Specialized web tasks in finance, biomedicine, and pharmaceuticals remain challenging due to missing domain priors: queries drift, evidence is noisy, and reasoning is brittle. We present WebExpert, a domain-aware web agent that we implement end-to-end, featuring : (i) sentence-level experience retrieval with topic merging and rule distillation, (ii) schemalight facet induction that bootstraps time,region,policy,industry facets from weak supervision instead of static hand-written lexicons, and (iii) preference-optimized planning that jointly improves query planning and retrieval via pairwise preference learning alongside a coverage-aware objective. At inference, a lightweight experience gate biases decoding toward active facets with fallback under low-retrieval confidence. On GAIA, GPQA, HLE, and WebWalkerQA, WebExpert improves Answer Exact Match (EM) by 1.5-3.6 pp over the strongest browsing baseline and reduces page hops. Analysis shows consistent gains and ablations on retrieval, topic merging, facet induction, and preference-aware training.
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。