No agent grades its own homework

说明与用途

当LLM代理审查自己的代码时，它会重复自己的错误。Agateon通过分离角色来解决此问题：编排器分配工作，新的子代理实现工作，独立的审查者在新上下文中使用机器检查的退出代码验证产物，从而消除回声并提高可靠性。

问题

When an LLM agent reviews its own output it echoes its own misunderstandings, missing bugs and misinterpretations.

结果

The new structure prevented two bad commits that existed only in logs, caught a writer agent’s fabricated anecdote, and ensured that verification was independent of author context, improving reliability.

工作流

• 1. Orchestrator reads state and dispatches a phase to a fresh subagent with only the brief and protocol files.
• 2. Subagent implements the task and writes output to a read‑only artifact.
• 3. Judge agent is spawned in a brand‑new session, receives only the artifact and spec, and runs automated tests, producing an exit code.
• 4. Acceptance gate checks the exit code; if it passes, the artifact is committed; if not, the orchestrator retries or aborts.
• 5. All retries and outcomes are logged with round number, failure mode, and prompt changes for auditability.

证据

We ran our whole engineering workflow this way, and it has caught things the author‑agent could not have caught: two bad commits that exist only in a log and never in git, an implementation sent back twice by a judge that had never seen our reasoning, and — a few days ago — a blog draft where a writer agent invented a personal anecdote to sound more human, which a fresh‑context reviewer flagged while the writer never noticed.

来源

The orchestrator never touches the artifact. It reads state, dispatches phases, and runs gate commands — read‑only verification, never file edits.

来源