Researchers propose a solution for smart manufacturing using LLM-based agents to generate production sequences, handle runtime faults, and coordinate over MQTT with real-time updates of the factory state.

A multi-agent LLM system improves personalized health checkup interpretation and guidance by executing tasks in parallel and synthesizing outputs. It outperforms single-agent systems in weighted LLM-judge score, usefulness, consistency, and handling of compound queries, but increases latency and cost.

This paper introduces ICR, a framework to evaluate communication in LLM multi-agent systems. It helps disentangle the effects of communication, architecture, and reasoning on system performance.

MAADBench is a new benchmark for anomaly detection in multi-agent systems (MAS) with evolving LLM backbones. It addresses challenges in MAS AD benchmarking by providing a refreshable paradigm with sampled-and-coupled generative tasks, refreshable trace generation, and automated label provision. The benchmark is designed to support diverse LLM backbones and offers a rich research agenda for MAS-specific anomaly detection.

A new benchmark, GT-HarmBench, was introduced to evaluate AI safety risks in multi-agent environments. The benchmark consists of 1,535 high-stakes scenarios, including game-theoretic structures, and measures the performance of 15 frontier models. The results showed that agents fail to choose socially beneficial actions in 38% of cases, and game-theoretic interventions improved outcomes by up to 18%. This provides a standardized testbed for studying alignment in multi-agent environments.