自主编码智能体的保证包络：软件变更的最小成本证据
原标题：Assurance Envelopes for Autonomous Coding Agents: Minimum-Cost Evidence for Software Change
AI 摘要
该论文提出「任务条件化保证包络」概念：当自主编码智能体回到已有软件时，需要从先前工程证据（测试、类型检查、契约、静态分析、监控轨迹）中选取最小成本子集，以重新建立本次变更必须保持的性质。作者将证据与组合规则形式化为带类型推理图，用前向链验证选择，并在来自 Rust、IronBlocks、Pong 等先前 AI 编码智能体运行结果的图上评估，另用 249 个合成图实例刻画计算复杂度。结果显示最小包络依赖具体任务，某些性质需多证据联合支持，且推导结构而非图规模决定求解难度。
正文节选
Assurance Envelopes for Autonomous Coding Agents: Minimum-Cost Evidence for Software Change Abstract When a coding agent returns to existing software, it inherits evidence from earlier engineering work: passing tests, type checks, discharged contracts, static analyses, and monitored traces. Reloading all of it is wasteful, but dropping a piece the change depends on can leave a required property unsupported. Given the properties a change must preserve, its obligations, we ask which least-cost sub