The agent did exactly what I asked. That was the bug.

说明与用途

LLM 代理按用户指令执行，但由于计划错误导致结果不正确。自动钩子无法检测此类错误。作者提出四项改进措施：基于决策的提示、原始来源验证、假设报告和独立验证工件，以提升计划验证。

问题

An LLM agent executed user requests correctly but produced incorrect results because the plan itself was flawed, and no tool call could detect the error.

结果

By shifting the focus from executing the user’s request to validating the request’s correctness, the author reduced the occurrence of plan-level failures and increased the reliability of agent-generated outputs.

工作流

• 1. Identify a task where the agent might follow a flawed plan. 2. Observe the agent’s correct execution but incorrect outcome. 3. Analyze why automated hooks cannot catch the error. 4. Implement four mitigations: decision-based prompts, primary source verification, assumption reporting, and independent artifact checks. 5. Apply mitigations to future tasks and monitor for improved error detection.

证据

The agent is a premise-taker. It will interrogate its own implementation all day and will not touch the frame of the request, because the frame came from you and you're the one it's trying to satisfy.

来源

I asked for a marketing asset. What found the bug was that a GIF is looked at by a human with eyes, and every assertion I had written shared an assumption with the code it was testing.

来源

Four things I changed, in rough order of how much they've paid off.

来源