MasterControl Seventeen Every Time

Abstract: 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.

摘要： 我们研究了一种用于企业分析的受控方法：由语言模型负责解读问题，同时通过确定性策略选择并运行预先批准的分析程序，该程序能够同时返回结果和证据。我们证明，在定义的分析类别内，通过使用关系运算以及聚合、比较、窗口、排序和相似度计算，这种限制依然能够保持足够的表达能力。

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.

固定的语义、策略、数据和执行规则也使得结果具有可重现性。在 440 次运行中，三个 8B 参数模型在运行时生成 SQL 并选择工具，而 Qwen3-8B 仅负责解读意图，并由策略执行已批准的程序。在 330 次运行时规划任务中，没有一个能够完全满足所有测试数据集的“答案与证据”契约；而策略执行的分析器则在 110 次测试中全部匹配成功。这是一个特定配置下的结果，并不代表运行时智能体在其他设计下无法取得成功。

Paper Details:

Title: MasterControl Seventeen Every Time
Authors: MasterControl AI Lab
Subject: Artificial Intelligence (cs.AI)
arXiv ID: 2609.03209
Submission Date: 2 Sep 2026

论文详情：

标题： MasterControl Seventeen Every Time
作者： MasterControl AI Lab
学科： 人工智能 (cs.AI)
arXiv ID： 2609.03209
提交日期： 2026 年 9 月 2 日