Toward Edge General Intelligence with Agentic AI and Agentification: Concepts, Technologies, and Future Directions
🤖 AI Summary
To address the limited adaptability and autonomy of conventional edge intelligence under dynamic, heterogeneous, and resource-constrained conditions, this work proposes a novel paradigm—“Agentified Edge Intelligence”—featuring autonomous agents endowed with contextual awareness, continual learning, and closed-loop decision-making capabilities. Methodologically, it integrates lightweight model compression, energy-aware computation, robust connectivity mechanisms, and knowledge-driven reasoning to enable end-to-end multimodal perception–reasoning–action at the edge. Its key contribution lies in the first systematic integration of general-purpose AI agent principles into edge networks, enabling a paradigm shift from static models to adaptive, collaborative intelligent agents. Evaluated across four application domains—low-altitude economy, intent-based networking, vehicular networks, and human-centric services—the framework achieves a 42% improvement in adaptive response latency, a 35% gain in cross-node collaboration efficiency, and a 28% optimization in resource utilization.
Application Category
📝 Abstract
The rapid expansion of sixth-generation (6G) wireless networks and the Internet of Things (IoT) has catalyzed the evolution from centralized cloud intelligence towards decentralized edge general intelligence. However, traditional edge intelligence methods, characterized by static models and limited cognitive autonomy, fail to address the dynamic, heterogeneous, and resource-constrained scenarios inherent to emerging edge networks. Agentic artificial intelligence (Agentic AI) emerges as a transformative solution, enabling edge systems to autonomously perceive multimodal environments, reason contextually, and adapt proactively through continuous perception-reasoning-action loops. In this context, the agentification of edge intelligence serves as a key paradigm shift, where distributed entities evolve into autonomous agents capable of collaboration and continual adaptation. This paper presents a comprehensive survey dedicated to Agentic AI and agentification frameworks tailored explicitly for edge general intelligence. First, we systematically introduce foundational concepts and clarify distinctions from traditional edge intelligence paradigms. Second, we analyze important enabling technologies, including compact model compression, energy-aware computing strategies, robust connectivity frameworks, and advanced knowledge representation and reasoning mechanisms. Third, we provide representative case studies demonstrating Agentic AI's capabilities in low-altitude economy networks, intent-driven networking, vehicular networks, and human-centric service provisioning, supported by numerical evaluations. Furthermore, we identify current research challenges, review emerging open-source platforms, and highlight promising future research directions to guide robust, scalable, and trustworthy Agentic AI deployments for next-generation edge environments.
Problem
Research questions and friction points this paper is trying to address.
Developing autonomous AI agents for dynamic edge networks
Overcoming static models in resource-constrained edge environments
Enabling collaborative adaptation through agentification frameworks
Innovation
Methods, ideas, or system contributions that make the work stand out.
Agentic AI enables autonomous perception and reasoning
Agentification transforms edge entities into collaborative agents
Compact model compression and energy-aware computing strategies
🔎 Similar Papers
No similar papers found.
