不同搜索引擎提供不同决策线索，影响智能体的检索效率与判断质量。
Equal Accuracy, Unequal Evidence: Search APIs as Decision Surfaces for Tool-Using Agents
- 将搜索接口视为决策表面，分析其对智能体行为的影响
- 三款引擎在准确率相近（25-26/100）但证据分布差异显著
- 适合关注检索策略与资源消耗优化的研究者和开发者
搜索API是众多智能体的核心信息获取层，常作为最频繁使用的工具。传统搜索提供网址、标题和摘要片段以预览网页内容。由于完整页面获取成本高昂，智能体逐渐采用渐进披露机制：先查看摘要，再决定是否加载全文。现有评估多聚焦答案准确率，我们提出应将商业搜索API视为决策表面——即排序后的片段、网址与元数据共同决定智能体是否立即作答、重新搜索或耗费令牌打开页面。本研究使用一个冻结的GPT-5.4智能体，搭配search_web与fetch_page两个工具，在SEALQA-HARD的100个难题上，仅更换搜索服务提供商（Brave、Tavily、Firecrawl）。Kimi-K2.6模型标注了智能体可见的所有内容元素（网址、标题、摘要及必要时的完整页面），共生成6,869条有效判断。采用经审计的正确答案标签与语义匹配标准，允许格式与命名微小变体。结果显示三者准确率接近（25、25、26 / 100），但证据经济结构迥异：Brave的摘要富含黄金答案，Tavily将高价值网址集中于首位，Firecrawl则推动更广范围探索。同时引入表面矛盾至黄金网址比率，范围为0.92至2.59，表明提供商选择本质上是检索预算与策略的权衡，而非单纯召回问题。
原文摘要 · Abstract (English)
Search APIs are the fundamental retrieval layer for many agents and are often their most frequently used tool. Traditional search APIs provide URLs, titles, and snippets that preview website contents. Because full-page retrieval is token-intensive, agent retrieval architectures increasingly use progressive disclosure: the agent first sees snippets and then chooses whether to fetch full pages. In such systems, search API performance is often evaluated primarily by answer accuracy. We argue that a commercial search API is better understood as a decision surface: the ranked snippets, URLs, and metadata that determine whether an agent answers immediately, searches again, or spends tokens opening pages. We test this claim with one frozen GPT-5.4 agent, two tools (search_web and fetch_page), and 100 questions from SEALQA-HARD, varying only the search provider (Brave, Tavily, Firecrawl). A Kimi-K2.6 oracle labels every content element visible to the agent (URL, title, snippet, and fetched page, when fetched), producing 6,869 valid per-URL judgments. We use an audited correct-answer label, semantic match, which preserves exact matches while accepting harmless formatting and naming variants. Under this measure, the providers remain close (25, 25, 26 / 100), but their evidence economies differ sharply: Brave offers gold-answer-rich snippets, Tavily concentrates gold-supporting URLs at rank 1, and Firecrawl is associated with broader exploration under this fixed agent policy. We also introduce a surface contradiction-to-gold URL ratio, which varies from 0.92 to 2.59. Provider choice is therefore a retrieval-budget and policy decision, not merely a recall decision.
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。