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 multistep 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.

The recent development of single-cell genomics requires more powerful computational tools to differentiate between different phenotypes, and rare cell identification has been one of the most important problems in this area. Recent data-driven approaches usually adopt feature selection techniques to identify important genes for anomaly detection, which require extensive training data or domain knowledge from experts. In comparison, large language models (LLMs) have achieved certain progress in scientific research with strong generalization ability, which has shown potential in this area. In this paper, we make an attempt to comprehensively evaluate the performance of in-context learning with LLMs in rare cell identification. In particular, we carefully design a chain-of-thought prompt combining token probability analysis and cross-query comparison to generate scores to identify rare cells. From the experimental results on benchmark datasets, we find that LLMs are competitive compared to existing training-based methods, which demonstrates extensive potential for rare cell identification. Our source code and data are available at https://github.com/Hyan-Yao/InContextCells/.

The integration of autonomous vehicles into urban traffic has great potential to improve efficiency by reducing congestion and optimizing traffic flow systematically. In this paper, we introduce CoMAL (Collaborative Multi-Agent LLMs), a framework designed to address the mixed-autonomy traffic problem by collaboration among autonomous vehicles to optimize traffic flow. CoMAL is built upon large language models and operates in an interactive traffic simulation environment. Specifically, It utilizes a Perception Module to observe surrounding agents and a Memory Module to store strategies for each agent. The overall workflow includes a Collaboration Module that encourages autonomous vehicles to discuss the effective strategy and allocate roles, a reasoning engine to determine optimal behaviors based on assigned roles, and an Execution Module that controls vehicle actions using a hybrid approach combining rule-based models. Experimental results demonstrate that CoMAL achieves superior performance on the Flow benchmark. Additionally, we evaluate the impact of different language models and compare our framework with reinforcement learning approaches. It highlights the strong cooperative capability of LLM agents and presents a promising solution to the mixed-autonomy traffic challenge. The code is available at https://github.com/Hyan-Yao/CoMAL