摘要：当一个长程 Agent 自身的状态和自我报告恰恰是你无法信任的对象时，如何验证它？我们提出了一种 Agent 工具，其验证是结构性的，而不是事后进行的。一个确定性的 Executive 拥有全部信念；语言模型只能提交带类型的提案，且只有当行动前预注册的预测由代码与观测进行匹配验证后，某项主张才会被采纳。该工具具备两项特性，使其不仅能验证 Agent，也能验证自身所产生的科学结论：其一，当每个模块的写入错误、渲染尺寸或加盐金丝雀回显低于阈值时，每次运行都会自行判定为无效（前八次架构运行中有四次被判无效，且每次都定位到一个真实缺陷）；其二，一个渲染不可见的影子参考会在每个消融实验单元中编译完整系统本应提交的计划，因此即使被测试的机制已被移除，漂移指标仍然有定义。借助该工具，我们报告了关于所有长程 Agent 都会遭遇的一类故障的一个清晰、单变量结果：消融承诺机制会使目标放弃率从 0.00 翻转至 1.00，而绑定错误保持在 0.00 不变（每个实验单元三个随机种子，每次运行最多 394 个参考节拍，所有运行均经有效性门控）。相比之下，当绑定通道的修复机制被消融时，绑定通道不会以逐节拍漂移的形式重新出现——由于绑定由代码持有，该故障类别被结构性吸收，其唯一残留表现于上游一层，即假设形成的崩溃。我们在充分披露任务效能为零的前提下报告这些结果：在 ARC-AGI-3 上经过门控的 52 次运行中，完成关卡数为零；这一点被预注册为结构性否决条件。本文的贡献是面向 Agent 开发的验证方法论，以及该方法使之能够测量的漂移分解。

Abstract:How do you verify a long-horizon agent when its own state and self-reports are exactly what you cannot trust? We present an agent instrument built so that verification is structural rather than post-hoc. A deterministic Executive owns all belief; a language model may only file typed proposals, and a claim is admitted only when a prediction pre-registered before acting is matched against observation by code. Two properties make the instrument a verifier of its own science, not just of the agent: every run invalidates itself when per-organ write-error, render-size, or salted-canary-echo floors are breached (four of the first eight architecture runs were invalidated, each localizing a real defect); and a render-invisible shadow reference compiles the plan the full system would have committed in every ablation cell, so drift metrics are defined even where the mechanism under test has been removed. Using this instrument we report a clean, single-variable result on a failure every long-horizon agent suffers: ablating the commitment mechanism flips goal-abandonment from 0.00 to 1.00 while binding error stays flat at 0.00 (three seeds per cell, up to 394 reference beats per run, every run gated valid). The binding channel, by contrast, does not reappear as per-beat drift when its repair is ablated -- because binding is code-owned, the failure class is structurally absorbed, its only residue appearing one layer upstream as a collapse in hypothesis formation. We report these under full disclosure that task efficacy is null (zero level completions across 52 gated runs on ARC-AGI-3), pre-registered as a structural defeater. The contribution is a verification methodology for agent development and the drift decomposition it makes measurable.