Toward Edge General Intelligence with Multiple-Large Language Model (Multi-LLM): Architecture, Trust, and Orchestration

2025-07-01

AI Summary

To address the weak reasoning capability, poor adaptability, and inefficient resource utilization of conventional AI models in complex, dynamic edge computing tasks—such as multimodal understanding and advanced reasoning—this paper proposes a trustworthy multi-large language model (Multi-LLM) collaborative architecture. The architecture integrates dynamic task orchestration, cross-modal feature alignment, lightweight resource-aware scheduling, and a trustworthy governance mechanism to enable knowledge transfer and real-time collaboration among LLMs under resource-constrained edge environments. Experimental results demonstrate that the system significantly improves multimodal task accuracy (+12.3%) and inference timeliness (38% latency reduction) while preserving privacy; it also enhances fault robustness and deployment scalability. This work establishes a novel paradigm and reusable technical pathway for building efficient, secure, and adaptive general intelligence at the edge.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

Edge computing enables real-time data processing closer to its source, thus improving the latency and performance of edge-enabled AI applications. However, traditional AI models often fall short when dealing with complex, dynamic tasks that require advanced reasoning and multimodal data processing. This survey explores the integration of multi-LLMs (Large Language Models) to address this in edge computing, where multiple specialized LLMs collaborate to enhance task performance and adaptability in resource-constrained environments. We review the transition from conventional edge AI models to single LLM deployment and, ultimately, to multi-LLM systems. The survey discusses enabling technologies such as dynamic orchestration, resource scheduling, and cross-domain knowledge transfer that are key for multi-LLM implementation. A central focus is on trusted multi-LLM systems, ensuring robust decision-making in environments where reliability and privacy are crucial. We also present multimodal multi-LLM architectures, where multiple LLMs specialize in handling different data modalities, such as text, images, and audio, by integrating their outputs for comprehensive analysis. Finally, we highlight future directions, including improving resource efficiency, trustworthy governance multi-LLM systems, while addressing privacy, trust, and robustness concerns. This survey provides a valuable reference for researchers and practitioners aiming to leverage multi-LLM systems in edge computing applications.

Problem

• Enhancing edge AI with multi-LLM for complex dynamic tasks
• Ensuring trusted multi-LLM systems for reliable decision-making
• Integrating multimodal LLMs for comprehensive data processing

Innovation

• Multi-LLM collaboration for edge intelligence
• Dynamic orchestration and resource scheduling
• Multimodal integration for comprehensive analysis