检索工具能力时，模型会因源风格差异失效，提出用关键词指纹识别并解决此问题。
When Tool-Backed Skill Retrieval Fails: Source-Style Collapse in Executable Capability Retrieval
- 用查询的TF-IDF指纹识别源风格不匹配，提前预警检索失败
- 在4996个查询上，覆盖率从22.3%提升至86.1%
- 适用于依赖外部工具的智能体系统，尤其关注跨源一致性
大型智能体越来越依赖检索来获取外部能力。本文研究结构化工具和API中的检索环节，这类可执行技能需在规划、集成或行动前被准确识别。我们发现，即使能力语料库固定，检索层仍可能无声失效：在ToolRet数据集上，一个在特定源片段微调的检索器，在另一源片段上表现骤降，即使其与目标工具的词法重叠度（FT-1100）更高。这种现象称为源风格坍塌。查询端的TF-IDF指纹比语义或长度特征更有效标识潜在失败源，提供低成本匹配信号。我们提出ToolScout，一种基于该信号的源感知路由方法：在混合4,996个查询流中，基于TF-IDF的路由使覆盖率从22.3%提升至86.1%；在五个崩溃源中，仅20个匹配样本就使覆盖加权全局top-1代理得分从1.3%提升至53.9%。即使将工具重新渲染为可执行技能卡，该失效与路由行为依然存在，排除了原始API模式是唯一原因。
原文摘要 · Abstract (English)
Large-scale agents increasingly rely on retrieval to access external capabilities. We study this retrieval gate in structured tools and APIs, a measurable class of tool-backed executable skills that must be surfaced before an agent can plan, incorporate, or act. In this setting the retrieval layer can silently fail even when the capability corpus is fixed: on ToolRet, a retriever fine-tuned on one source-specific slice collapses on another source-specific slice of the same benchmark, with FT-1100 despite its higher lexical overlap with the gold tools. We call this failure mode source-style collapse. Query-side TF-IDF fingerprints flag source styles on which the fine-tuned retriever is likely to fail better than semantic or length-based proxies, giving a cheap signal for mismatch over a fixed tool corpus. We propose ToolScout, a source-aware routing method that uses this signal as a routing guard: on the mixed 4,996-query stream, TF-IDF-based routing raises coverage from 22.3% to 86.1%, and across five collapsed sources 20 matched examples raise the coverage-weighted global top-1 proxy from 1.3% to 53.9%. The same failure and routing behaviors persist when tools are rerendered as executable skill cards, which rules out raw API-schema format as the sole cause.
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。