让代码生成代理只能在有可验证证据时才推进状态，防止虚假完成。
Proof-or-Stop: Don't Trust the Agent, Trust the Evidence -- Loop Engineering for Verifiable Evidence-Gated Lifecycle Control
- 用可机械验证的证据作为状态转换的唯一依据，拒绝无证据的声明。
- 零误判完成（false-DONE），18类篡改被完全拦截，误接受率为零。
- 适合需要高可信度的自动化开发场景，尤其关注安全与可靠性。
自主代码代理执行多步软件任务，但评审、测试、完成等生命周期状态常缺乏实证支持。本文提出Proof-or-Stop生命周期控制机制，仅当具备新鲜、可追踪、源码绑定的机械可验证证据时，才允许状态转移。该方法将代理输出视为待验证的声明，而非状态本身；“证明”在此指在特定信任模型下符合门控要求的证据，而非程序语义正确性。通过机制测试、受控策略消融实验及自应用证据验证，结果表明：无需人工干预的循环引擎在10个场景中全通过，零误判完成；本地密钥接收包拒绝对18类篡改攻击，零误接受。在9,240单元消融实验中，预注册的A4 vs A2-prime对比显示，门控循环下可见通过/隐藏失败放大率从31/1,800降至2/1,800，不放大的准确率提升1.6个百分点（95%置信区间[0.8, 2.5]）。近计算量的A3 vs A4比较（14/1,800 vs 2/1,800）表明，收益源于强制审查为门控，而非简单增加评审者。自应用语料库包含565个故事、1,007条评审发现，94.8%已解决，并含68行跨厂商高危/关键问题展示。结果支持Proof-or-Stop作为模型无关、宿主中立的控制层，决定哪些代理声明可触发生命周期动作。评估限于单一模型族、24项消融任务及自托管语料库。
原文摘要 · Abstract (English)
Autonomous coding agents increasingly execute multi-step software work, but lifecycle states such as reviewed, tested, DONE, and ready-to-merge remain claims unless supported by current evidence. We present Proof-or-Stop Lifecycle Control, a method that permits lifecycle transitions only when fresh, tracked-source-state-bound, mechanically verifiable evidence satisfies the relevant gate. The method treats agent outputs as claims rather than lifecycle state, and uses proof operationally to mean gate-admissible evidence under a stated trust model, not semantic program correctness. We evaluate an open-source implementation through mechanism tests, a powered control-policy ablation, and operated self-application evidence. The unattended-loop engine passed 10 of 10 scenarios with zero false-DONE, and local-key receipt bundles rejected 18 tamper classes with zero false accepts. In a 9,240-cell ablation, the pre-registered A4 versus A2-prime comparison reduced visible-pass/hidden-fail amplification from 31 of 1,800 injected cells under a compute-budgeted naive loop to 2 of 1,800 under the gated loop, a 1.6 percentage-point improvement in not-amplified rate with a 95 percent confidence interval of [0.8, 2.5]. A near-compute A3 versus A4 comparison, 14 of 1,800 versus 2 of 1,800, indicates that the gain is associated with enforcing review as a lifecycle gate rather than merely adding a reviewer. The self-application corpus contains 565 stories and 1,007 review findings, with 94.8 percent resolved, plus a 68-row high/critical cross-vendor exhibit. These results support Proof-or-Stop as a model-agnostic, host-neutral control layer for deciding which autonomous-agent claims a lifecycle may act on. The evaluation is limited to one model family, 24 ablation tasks, and a self-hosted corpus.
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。