While Large Language Model-based Multi-Agent Systems (MAS) consistently outperform single-agent systems on complex tasks, their intricate interactions introduce critical reliability challenges arising from communication dynamics and role dependencies. Existing Uncertainty Quantification methods, typically designed for single-turn outputs, fail to address the unique complexities of the MAS. Specifically, these methods struggle with three distinct challenges: the cascading uncertainty in multi-step reasoning, the variability of inter-agent communication paths, and the diversity of communication topologies. To bridge this gap, we introduce MATU, a novel framework that quantifies uncertainty through tensor decomposition. MATU moves beyond analyzing final text outputs by representing entire reasoning trajectories as embedding matrices and organizing multiple execution runs into a higher-order tensor. By applying tensor decomposition, we disentangle and quantify distinct sources of uncertainty, offering a comprehensive reliability measure that is generalizable across different agent structures. We provide comprehensive experiments to show that MATU effectively estimates holistic and robust uncertainty across diverse tasks and communication topologies.

Generating high-quality question–answer (QA) pairs for specialized technical domains is essential for advancing knowledge comprehension, yet remains challenging. Existing methods often yield generic or shallow questions that fail to reflect the depth and structure of expert-written examples. We propose ExpertGenQA, a generation protocol that combines few-shot prompting with dual categorization by topic and question style to produce more diverse and cognitively meaningful QA pairs. ExpertGenQA achieves twice the efficiency of standard few-shot methods while maintaining 94.4% topic coverage. Unlike LLM-based judges, which often favor surface fluency, Bloom’s Taxonomy analysis shows that ExpertGenQA better captures expert-level cognitive complexity. When used to train retrieval systems, our questions improve top-1 accuracy by 13.02%, demonstrating their practical value for domain-specific applications.