为AI路由设计可审计的运行时凭证，让用户看清模型如何被调用。
Model Routing as a Trust Problem: Route Receipts for Adaptive AI Systems
- 提出路由凭证概念，记录每次请求的实际路径选择。
- 现有平台已有碎片化路由信息，但缺乏统一可移植的记录。
- 适合关注AI可信性与可追溯性的开发者和监管者使用。
AI产品常通过版本别名、服务层级、工具选择、区域端点、回退规则或安全处理等路由步骤来响应请求。这些路由机制广泛存在于主流AI平台与服务架构中，虽能提升成本效益、速度与可用性，却也影响用户信任。当路由改变响应的成本、质量或责任归属而用户无法察觉时，信任即可能破裂。仅知‘哪个模型回答’是不够的，实际运行路径同样关键。自适应AI系统应生成一种名为‘路由凭证’的运行时透明文档，它是一个紧凑的请求路径记录，包含足够事实以供依赖输出者重构重要路由决策，同时不暴露专有内部逻辑或隐藏推理。路由透明性应纳入模型文档体系：模型卡描述训练好的模型，而路由凭证则描述特定回答产生的运行时条件。本文提出路由凭证概念、最小化数据模式及红移模型，并基于文档调研部分主流平台，发现其已存在路由信息片段，但缺乏每条回答对应的可移植记录。
原文摘要 · Abstract (English)
AI products often route requests through version aliases, service tiers, tool choices, regional endpoints, fallback rules, or safety handling before responding. These routing steps are documented product surfaces in several widely used AI platforms and serving stacks. Routing helps AI services stay affordable, fast, and available at scale, and it shapes trust. Trust can break when routing changes the cost, quality, or accountability of a response without the user being able to tell what happened. "Which model answered?" is only part of the audit question. The runtime path matters. Adaptive AI systems should produce a runtime transparency artifact called the route receipt. A route receipt is a compact record of the route that served a request. It should capture enough material facts for people relying on the output to reconstruct important routing decisions without exposing proprietary internals or hidden reasoning. Route transparency should be part of model documentation. Model cards describe trained model artifacts, while route receipts describe the runtime conditions under which a particular answer was produced. The paper introduces the route-receipt concept, a minimal schema and redaction model, and a documentation-based survey of selected platforms showing that receipt fragments already exist without a portable per-answer record.
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。