Do More Agents Help? Controlled and Protocol-Aligned Evaluation of LLM Agent Workflows

Yuhang Fu, Ruishan Fang, Jiaqi Shao, Huiyu Zheng, Zhengtao Zhu, Bing Luo, Tao Lin

Jun 5, 2026 at 04:00

2 Views

0 Comments

arXiv:2606.05670v1 Announce Type: new Abstract: Does adding more agents help an LLM workflow once compared systems share the same benchmark loader, tool access, answer contract, usage accounting, and trajectory logging? We introduce BenchAgent, an evaluation framework that places single-agent, fixed multi-agent (MAS), and evolving MAS workflows...

Read the full article at the source.

Read Original Article

Was this helpful?