The Coding Agent That Can't Grade Its Own Homework

说明与用途

agent‑loop 框架将代码生成拆分为多个阶段，使用文件交接和独立验证，消除自我确认并提供可审计的流程。

问题

Coding agents often self‑grade, leading to false “All tests pass” messages and noisy, biased outputs.

结果

Agent‑loop delivers deterministic, verifiable code changes with a clear audit trail, preventing self‑confirmation bias and ensuring tests are actually run.

工作流

• 1. Triage: classify task into S, M, or L tier
• 2. Analyze (M/L): generate analysis.md
• 3. Plan (M/L): produce plan.md with runnable check
• 4. Implement (S/M/L): create implementation.md
• 5. Verify: run independent verifier on plan and diff, output PASS/FAIL
• 6. Debug (on FAIL): up to 3 iterations, each with fresh context and re‑verification

证据

The verifier never sees the reasoning

来源

The debug loop caps at 3 iterations

来源