UMAS: System-Level Uncertainty Quantification for Multi-Agent LLM Systems
Multi-Agent Systems (MAS) are a promising paradigm for improving the reasoning capabilities of large language models, yet they remain prone to hallucinations and erroneous outputs. Uncertainty Quantification (UQ) is crucial for assessing system reliability, but existing methods are largely designed for single-agent set...
Han Li, Jinhao Duan, Xiao-Shuang Shi et al.
· 0 citations