Perplexity 测试多智能体团队:四人团队在 WANDR 上全面跑赢单模型
Perplexity 用 WANDR 基准实测了多智能体团队:每个四人团队分数都比单模型高,四个里还有三个跑得更快。想给自己的 agent 项目做编排的话,这个数据很值得参考。
Perplexity 在 WANDR 基准上测试多智能体团队协作的效果,结果显示每个四人团队的成绩都高于对应模型单独运行时的表现。
在四个团队中,有三个不仅分数更高,完成任务的速度也更快,说明多智能体分工在质量和耗时两个维度上都能带来收益。
这次实验的意义在于验证了"团队式"智能体编排相对单体模型的实际优势,为开发者设计复杂任务的 agent 架构提供了直接的基准数据参考。
Teams of agents also complete tasks sooner. When testing teams on WANDR, Every team of four scored higher than its model alone, and three of the four finished sooner.📊 2 ⚡
This report is categorized under AITOP's "Papers" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Perplexity, WANDR, agents, multi-agent systems.
Source attribution: curated from Perplexity (@perplexity_ai).