Harmonized System (HS) tariff classification is a high-stakes, expert-level task in which a free-form product description must be mapped to a specific six- or eight-digit code under the General Interpretive Rules (GIR), section notes, chapter notes, and Explanatory Notes. The difficulty lies not in knowledge volume but in *multi-dimensional rule reasoning*: a correct classification must satisfy competing priority rules along several axes simultaneously, including material, form, function, essential character, the part-versus-whole boundary, and specific listing versus residual headings. End-to-end prompting of large language models fails characteristically by resolving one axis while ignoring the priority constraints on the others. We present a *deterministic agentic workflow* in contrast to self-planning agents: the control flow is fixed, language model calls are confined to narrow stages, and reflection and verification are retained as local mechanisms. This design yields interpretability by construction--each decision is decomposed into stage-wise structured outputs with verbatim citation of the chapter or section notes that bear on it. The architecture combines offline knowledge-engineering of the Chinese HS tariff with an online six-stage pipeline. Evaluated on HSCodeComp at the six-digit level, the workflow reaches 75.0% top-1 and 91.5% top-3 at four digits, and 64.2% top-1 and 78.3% top-3 at six digits with Qwen3.6-plus; an open-weight Qwen3.6-27B-FP8 backbone in non-thinking mode achieves 84.2% four-digit and 77.4% six-digit top-1 agreement with the frontier model. A two-stage manual audit of 226 six-digit disagreements suggests that a non-trivial fraction of HSCodeComp ground-truth labels may deviate from HS general rules; full adjudication records are released in the appendix as preliminary findings for community review.

翻译：协调制度（HS）关税分类是一项高风险、专家级任务，需将自由形式的产品描述映射到《通用解释规则》（GIR）、类注、章注及注释所规定的特定六位或八位代码。其难点不在于知识体量，而在于**多维规则推理**：正确的分类必须同时满足材料、形态、功能、基本特征、部分与整体边界、具体列名与未列名税号等多条相互竞争的优先级规则。端到端提示大型语言模型的方式存在固有缺陷——它可能解决某一维度上的问题，却忽略了其他维度上的优先级约束。我们提出一种**确定性代理工作流**，区别于自规划代理：其控制流固定，语言模型调用仅限于狭窄阶段，而反思与验证作为局部机制保留。这一设计通过构造实现可解释性——每个决策被分解为阶段性的结构化输出，并逐字引用与之相关的类注或章注。该架构将中国HS关税的离线知识工程与在线六阶段流水线相结合。在六位码级别的HSCodeComp评估中，该工作流结合Qwen3.6-plus模型，四位码达到75.0%的Top-1准确率和91.5%的Top-3准确率，六位码达到64.2%的Top-1准确率和78.3%的Top-3准确率；采用开放权重Qwen3.6-27B-FP8骨干模型（非思考模式）时，四位码和六位码的Top-1准确率分别与前沿模型达到84.2%和77.4%的一致性。对226项六位码分歧进行的两阶段人工审计表明，HSCodeComp中相当比例的真实标签可能偏离HS通用规则；完整裁决记录作为初步发现附录发布，供社区审阅。