Jev-LiteMAS: Separating Decisions from Generation in Multi-Agent Workflows
arXiv:2610.21411v1 Announce Type: new Abstract: Multi-agent LLM systems rely on generative models for expert execution, workflow planning, and artifact review. Yet many coordination operations require only bounded decisions, such as selecting the next expert or judging artifact quality. Profiling three representative MAS frameworks, we find that routing and review account for 31.7-43.5% of generative-LLM tokens. However, replacing these operations with low-cost decision models introduces two in…