研究显示 AI 智能体团队成本是单体的 1.8 到 5.1 倍而质量提升微弱
AI agent teams waste massive tokens for barely measurable quality gains, research finds
- 1评测公司 Vals AI 实测 GPT-6 Sol 与 Claude Opus 5.5，智能体团队成本为单体的 1.8 到 5.1 倍
- 2四组团队与单体对比仅一组统计显著，GPT-6 Sol 在中等推理强度下高出 7.3 分
- 3Anthropic 自测显示智能体从 10 个扩到 100 个，Opus 5.5 在 24 小时后得分仅小幅上升
- 4OpenAI 研究员 Noam Brown 称多智能体买到的主要是速度，四个智能体快一倍也贵一倍
多智能体团队买到的主要是速度而不是质量，当模型已在最高推理强度运行时，加人几乎不再带来质量收益。
- 影响：为质量扩大智能体规模，token 成本可达单体 1.8 到 5.1 倍而收益大多不显著；可并行的网页调研、数学类任务能以加人换速度，写作类任务加人基本无效；协调开销会随规模放大。
- 参考：可考虑先按任务可并行度筛选场景，只对网页调研、数学推理类任务小规模试点多智能体并记录成本与质量对比；在扩大集群规模前，先算清单个智能体在最高推理强度下的基线成本。
- 依据：Vals AI 在 Vibe Code Bench 的四组对比仅一组统计显著，属第三方评测；Anthropic 的递减数据为自家测试口径；Noam Brown 的说法出自 Dwarkesh 播客。
Oct 11, 2026
AI agent teams deliver almost no better results than single agents, research finds.
Evals company Vals AI tested GPT-6 Sol and Claude Opus 5.5 on the "Vibe Code Bench," both solo and as teams, at two reasoning levels: medium and maximum reasoning effort. The teams cost between 1.8x and 5.1x more than single agents.
Out of four comparisons between teams and solo agents, only one showed a statistically significant improvement: GPT-6 Sol at medium reasoning, where the team scored 7.3 points higher. At maximum reasoning, the team setup gave neither Sol nor Opus 5.5 any real advantage. The results suggest that the extra cost of agent teams isn't worth it in most cases, especially when models are already running at full compute.
Anthropic saw quality gains shrink as it added more agents in two of its own tests with Opus 5.5. Larger teams reached a given performance level faster, but going from ten to 100 agents only nudged scores up slightly after 24 hours. In separate ProgramBench tests, speed gains came with higher token usage.
| Task with Opus 5.5 | 1 agent | 10 agents | 30 agents | 100 agents |
|---|---|---|---|---|
| Knowledge base | 0.53 | 0.70 | 0.71 | 0.74 |
| Lean Theorem Proving | 0.39 | 0.66 | 0.66 | 0.68 |
Fable 5.1 showed stronger quality gains on the Lean theorem proving task above ten agents, but still scored below Opus 5.5 across all tests. On the knowledge base task, Fable's score actually dipped slightly when scaling from 30 to 100 agents.
More agents buy speed but not better output
OpenAI researcher Noam Brown confirmed in the Dwarkesh Podcast that multi-agent systems mainly buy speed, not better quality. Four agents solved tasks twice as fast but also cost twice as much. At 16 agents, the pattern held but grew slightly less efficient.
The effect depends heavily on the task. Web research and math parallelize well, but writing a novel doesn't, he said. Throwing 10,000 agents at a novel would be just as pointless as throwing 10,000 people at it. Brown acknowledged that scaling to very large numbers of agents remains largely unexplored because the costs are simply too high.
OpenAI developer Eric Provencher recently warned against using agent swarms for exactly this reason. They're most likely wasted money, he argued, because coordination between agents breaks down. He called it the coordination tax.
AI News Without the Hype – Curated by Humans
Subscribe to THE DECODER for ad-free reading, a weekly AI newsletter, our exclusive "AI Radar" frontier report six times a year, full archive access, and access to our comment section.
- Full access to every article on THE DECODER
- No ads
- Join the comments and community discussions
- A weekly AI news recap via mail
- 6x/year: "AI Radar" — deep dives on the AI topics that matter most
- Daily AI news, always up to date
- Our full ten-year archive
- Covered by a team with 10+ years in AI
来源：The Decoder：AI News · the-decoder.com