长周期智能体可靠性：99%单步成功率为何不够

摘要

单步成功率99%时，10步任务无失败完成的概率约90%，100步降至37%；若每次失败可重试一次且失败相互独立，37%可升至约99%。但重试并不简单：响应超时可能导致动作重复执行，失败也可能改变系统状态，且失败未必独立。因此长周期智能体不只是大语言模型问题，周边系统同样关键。

摘要由模型根据原文撰写，以原文为准。

99% reliability sounds great but you should really do the math.

If each action succeeds 99% of the time, a 10-step task has a 90% chance of finishing without a single failure. At 100 steps, that drops to 37%.

Now give each failed action one retry. Assuming independent failures, that 37% jumps to ~99%.

Thats a huge difference. But retries aren’t always that simple.

What if an action succeeded but the response timed out? Retrying could execute it twice. What if the failure left the system in a different state? They are probably also not independent.

You need to know what actually happened before deciding what to do next.

This is why long-horizon agents aren’t just an LLM problem. Better models are definitely needed, but the systems around them matter just as much!

长周期智能体可靠性：99%单步成功率为何不够

摘要

正文 · 原文

引用原文