AIBullisharXiv – CS AI · Mar 177/10
🧠
Training-Free Agentic AI: Probabilistic Control and Coordination in Multi-Agent LLM Systems
Researchers introduce REDEREF, a training-free controller that improves multi-agent LLM system efficiency by 28% token usage reduction and 17% fewer agent calls through probabilistic routing and belief-guided delegation. The system uses Thompson sampling and reflection-driven re-routing to optimize agent coordination without requiring model fine-tuning.