每一次，都是 MasterControl 十七

摘要

我們研究一種受治理的企業分析方法：語言模型詮釋問題，而確定性策略則選擇並執行預先核准的分析程序，該程序會回傳結果與證據。我們展示，此限制在界定的分析類別內仍可保有表達力，其使用關聯運算，加上聚合、比較、視窗、排序與相似度。固定的語意、策略、資料與執行規則也使結果可重播。在 440 次執行中，三個 8B 模型在執行時產生 SQL 並選擇工具，而 Qwen3-8B 僅詮釋意圖，並由策略執行已核准的程序。在 330 個執行時規劃回合中，沒有任何一個能在所有測試資料集上符合完整的答案與證據契約；受策略執行的分析器則在 110 個中符合 110 個。這是特定組態下的結果，並非執行時代理在其他設計下無法成功的證據。

English

We study a governed approach to enterprise analytics: a language model interprets the question, while deterministic policy selects and runs a pre-approved analytical program that returns both results and evidence. We show that this restriction can remain expressive within a defined analytical class, using relational operations plus aggregation, comparison, windows, ranking, and similarity. Fixed meaning, policy, data, and execution rules also make results replayable. Across 440 runs, three 8B models generated SQL and selected tools at runtime, while Qwen3-8B interpreted intent only and policy executed the approved program. None of 330 runtime-planning episodes matched the full answer-and-evidence contract across all test datasets; the policy-executed analyzer matched 110 of 110. This is a configuration-specific result, not evidence that runtime agents cannot succeed under other designs.