Training-Free Agentic AI: Probabilistic Control and Coordination in Multi-Agent LLM Systems
Published in arXiv, 2026
This paper presents a training-free approach to building agentic AI systems with probabilistic control and coordination in multi-agent LLM settings. We propose methods for orchestrating multiple LLM agents without requiring additional fine-tuning, enabling scalable and flexible multi-agent collaboration through probabilistic decision-making frameworks.
Recommended citation: @article{hosseini2026trainingfree, title={Training-Free Agentic AI: Probabilistic Control and Coordination in Multi-Agent LLM Systems}, author={Hosseini, Mohammad-Parsa and Shah, Ankit and Qureshi, Saiyra and Huang, Alex and Miao, Connie and Wei, Wei}, journal={arXiv}, year={2026} }
Download Paper