AINeutralarXiv – CS AI · 7h ago6/10
🧠
Scaling Behavior of Single LLM-Driven Multi-Agent Systems
Researchers demonstrate that multi-agent LLM systems exhibit diminishing returns as agent count increases, challenging the assumption that more agents automatically improve performance. The study reveals that optimal scaling depends on base model capability, task type, and interaction design, with coordination overhead—not context limitations—driving performance degradation.