The field of multi-agent systems and large language models is rapidly evolving, with a focus on developing innovative frameworks and approaches to address the challenges of collaboration, coordination, and verification. Recent developments have highlighted the importance of verification-aware planning, adaptive trust management, and explainable decision-making in enabling reliable and efficient multi-agent systems. The integration of large language models into multi-agent systems has shown significant promise in improving performance, robustness, and interpretability. Notably, the development of frameworks that enable adaptive and explainable urban sensing, as well as scalable and cost-aware communication strategies, has the potential to transform various applications, including smart city management and collaborative workflows.

Noteworthy papers include: Verification-Aware Planning for Multi-Agent Systems, which introduces a framework for multi-agent collaboration with verification-aware planning, enabling reliable coordination and iterative refinement. SORA-ATMAS, which presents an adaptive trust management and governance framework for future smart cities, effectively steering multiple large language models towards domain-optimized outputs. AgentSense, which introduces a hybrid framework that integrates large language models into participatory urban sensing, offering distinct advantages in adaptivity and explainability. Communication to Completion, which establishes a theoretical foundation for measuring communication effectiveness in multi-agent systems and a practical framework for complex collaborative tasks.