Multi-agent LLM frameworks are data-intensive systems that govern how agents orchestrate tasks, manage state, and coordinate decisions. These architectural choices control execution overhead, memory behavior, planning effectiveness, and coordination scalability. Their impact on system performance remains poorly understood. Existing benchmarks evaluate individual agent capabilities in isolation and lack standardized framework-level comparison. We make four contributions. We introduce an architectural taxonomy that decomposes multi-agent LLM frameworks along five dimensions: orchestration, memory, planning interfaces, specialization, and communication topology. We develop MAFBench, a unified evaluation suite that integrates existing benchmarks within a standardized execution pipeline. We conduct a controlled empirical study across nine frameworks, fixing the underlying LLM and varying only architectural design choices. We distill the results into six evidence-based design principles. Architectural design, not only model intelligence, governs performance. Orchestration alone increases latency by over 60x, and a minimal implementation of the same paradigm isolates that cost as implementation rather than paradigm. Schema-constrained planning interfaces reduce accuracy by up to 32 points through formatting failures, not reasoning errors. Communication topology drops coordination success from above 90% to below 30% under mismatched structure. Memory architecture controls recall and scalability independent of context window size, and no evaluated framework natively supports controlled knowledge revision.
Quantum Artificial Intelligence for Mission-Critical Systems: Foundations, Architectural Elements, and Future Directions
Quantum Cloud Computing and Distributed Systems (qCLOUDS) Laboratory, School of Computing and Information Systems, The University of Melbourne(量子云计算与分布式系统实验室,计算与信息系统学院,墨尔本大学)
Generative AI Models for Different Steps in Architectural Design: A Literature Review
School of Architecture, Tianjin University(天津大学建筑学院);Graduate School of Advanced Science and Technology, Japan Advanced Institute of Science and Technology(日本先进科学技术学院先进科学技术研究院)
Augmented Computational Design: Methodical Application of Artificial Intelligence in Generative Design
Eindhoven University of Technology(埃因霍温理工大学);Nieman Raadgevende Ingenieurs(尼曼咨询工程公司);Delft University of Technology(代尔夫特理工大学);University of Twente(特文特大学)
Preserving Decision Sovereignty in Military AI: A Trade-Secret-Safe Architectural Framework for Model Replaceability, Human Authority, and State Control
College of Plant Protection(植物保护学院);The Institute of Energetic Paradigm(能量范式研究所);Southwest University, China(西南大学)
HAAS: A Policy-Aware Framework for Adaptive Task Allocation Between Humans and Artificial Intelligence Systems
organization= Valencian Research Institute for Artificial Intelligence (VRAIN), Universitat Polit\`ecnica de Val\`encia , addressline= Camino de Vera s/n , city= Valencia , country= Spain