循环并非可靠性保障：智能代码修复的状态约束证据与类型化修订契约
Looping Is Not Reliability: State-Bound Evidence and Typed Revision Contracts for Agentic Code Repair
浏览论文内容
中文总结 AI 辅助
研究编码智能体中生成-测试-修订循环的可靠性问题，通过实验揭示相关差距及问题，提出证据约束的类型化循环契约并实例化其可机械执行子集，实现规范与工件，非证明修复能力提升等。
中文摘要 AI 辅助
在编码智能体中，生成-测试-修订循环很常见，但仅靠重复无法保证可靠性。我们研究了找到正确补丁与保留、验证并提交补丁之间的差距。通过对30个人类评估修复的密封五种子研究产生了900条三修订轨迹。强制修订下，当前正确性随当前轨迹从一次修订后的0.820降至两次修订后的0.673，不过一直正确的比例升至0.847。两项常见状态研究使用相同冻结程序的2430个分支以消除后处理风险集偏差。在预指定的14B复制中，陈旧轨迹对135个正确起始中的34个造成损害，而当前轨迹为4个，增加了22.2个百分点。前瞻性的540次推出策略消除了观察到的正确起始损害，但减少了错误起始修复且未达到联合标准。对24个错误和四个编码员堆栈的存储库实验揭示了下限效应和组件异质性但无显著影响。因此我们分离了准入、保存、有根据的认证、能力和活性。我们得出了一个证据约束的类型化循环契约，并在一个参考实现中实例化其可机械执行的子集，该实现将验证者证据与精确代码状态绑定，保留已验证的检查点，并发出可审计的准入收据。该实现是一个可执行规范和一致性工件，而非修复能力提高或校准验证者依赖性的证据。
英文摘要
Generate--test--revise loops are common in coding agents, but repetition alone provides no reliability guarantee. We study the gap between finding a correct patch and retaining, verifying, and submitting it. A sealed five-seed study over 30 HumanEval repairs produces 900 three-revision trajectories. Under forced revision, current correctness with current traces falls from 0.820 after one revision to 0.673 after two, although ever-correct rises to 0.847. Two common-state studies use 2,430 branches from identical frozen programs to remove post-treatment risk-set bias. In a prespecified 14B replication, stale traces harm 34/135 correct starts versus 4/135 with current traces, a 22.2-point increase (task-cluster 95\% CI $[8.9,37.0]$, exact Holm $p=0.0337$). A prospective 540-rollout policy eliminates observed correct-start harm but reduces wrong-start repair and fails its joint criterion. Repository experiments over 24 bugs and four coder stacks expose floor effects and component heterogeneity without Holm-significant effects. We therefore separate admission, preservation, grounded certification, competence, and liveness. We derive an evidence-bound typed loop contract and instantiate its mechanically enforceable subset in a reference implementation that binds verifier evidence to exact code states, preserves verified checkpoints, and emits auditable admission receipts. The implementation is an executable specification and conformance artifact, not evidence of improved repair competence or calibrated verifier dependence.
发表机构
- Alibaba Cloud（阿里云）
机构由 AI 辅助整理，请以论文原文为准。
