Cohere 论文：多智能体编码团队宜由强模型领队、便宜模型只做规划
Cohere Labs 论文《Scaling Inference-Time Compute with Teams of Coding Agents》发现，多智能体编码团队虽优于单 agent，但成本高出 3 到 7 倍。
Rohan Paul· @rohanpaul_ai · X·2026-10-19 13:10· 59 分钟前AI 评分58
AI 导读
Cohere Labs 论文《Scaling Inference-Time Compute with Teams of Coding Agents》研究多智能体编码团队的算力分配，发现团队超过单 agent 但成本高出 3 到 7 倍。
正文 · 原文
New Cohere paper finds that a team of coding agents gets the most from extra agents when they only research and plan, and cheap models can do that job for a strong lead at far lower cost.
A team of coding agents beats 1 agent working alone, but costs 3 to 7 times as much. More agents can also mean duplicate work and extra code to merge.
The researchers built a lead agent that hands subtasks to workers, then varied the workers' role, model and count. On ProgramBench, agents rebuild a whole program from just a working executable and its docs.
Workers that only plan matched the reward of workers used in every stage, at half the cost. A strong GPT-5.6 Sol lead with 16 cheap Luna planners came within 1.4 points of an all-Sol team at 70% lower cost.
On tasks like this, put your strongest model in the lead and use cheap models only for planning, since cheap coders lowered reward.
来源：Rohan Paul · x.com
来源：RadarAI · aihot.news