# OpenAI Codex 开发者称超过两个并行子智能体是浪费 token 的陷阱

- 来源：The Decoder：AI News（RSS）
- 作者：Matthias Bastian
- 发布时间：2026-09-17 19:03
- AIHOT 分数：56
- AIHOT 链接：https://aihot.news/items/cmu5fuq4j0803ro7nge9iscm8
- 原文链接：https://the-decoder.com/ai-agent-swarms-are-a-massive-waste-of-tokens-with-zero-quality-gain-says-openai-codex-developer

## AI 摘要

OpenAI Codex 开发者 Eric Provencher 在 X 上警告，超过两个并行子智能体几乎总是烧掉大量 token 却不提升质量，因为智能体互不信任会互相重复检查，他称之为协调税。

## 正文

Eric Provencher, a Codex developer at OpenAI, is warning against reckless token spending in agentic workflows. In posts on X, he argues that more than two parallel sub-agents almost always burn tokens without improving quality. Agents don't trust each other, so they end up "double-checking everyone's homework."

Provencher calls this the "coordination tax" and says it's "really hard to keep so many parallel lanes running without spinning out and burning tokens on excessive verification." When a project surfaced where someone spent $20,000 in tokens refactoring a single Python file with 1,393 Fable agents, he commented that a single Astra agent could have done it for a "fraction of the cost." Agent swarms may save time, but the token overhead is a "trap," he writes.

Running more than two sub-agents at a time burns tokens for zero quality gain, says Provencher. | Image: via X

As a fix, he recommends delegating tasks to separate threads that only notify the main agent once done, instead of constantly polling for status. System prompts also get executed multiple times across sub-agents, and sub-agents often lack needed context, causing redundant work. Provencher acknowledges OpenAI still needs to ship better solutions here.