Edge General Intelligence Through World Models, Large Language Models, and Agentic AI: Fundamentals, Solutions, and Challenges
Периферийный общий интеллект на основе мировых моделей, больших языковых моделей и агентного искусственного интеллекта: основы, решения и проблемы
2026-01-01
SCID: 54.1/7vhrvpwz
Discuss with AI
Edge General Intelligenceagentic artificial intelligenceimagination-based planninglarge language modelsworld models
Figures from the paper
Abstract (AI)
Edge General Intelligence (EGI) represents a transformative evolution of edge computing, where distributed agents possess the capability to perceive, reason, and act autonomously across diverse, dynamic environments. This vision is increasingly realized through agentic artificial intelligence (AI) systems, which often leverage large language models (LLMs) for complex reasoning and planning. However, language-based reasoning alone struggles to capture high-dimensional physical dynamics. Central to overcoming this challenge are world models, which act as proactive internal simulators that not only predict but also actively imagine future trajectories, reason under uncertainty, and plan multi-step actions with foresight. This proactive nature allows agents to anticipate potential outcomes and optimize decisions ahead of real-world interactions. While prior works in robotics and gaming have showcased the potential of world models, their integration into the wireless edge for EGI remains underexplored. This survey bridges this gap by offering a comprehensive analysis of how world models can empower agentic systems at the edge, enhancing their foresight beyond the limits of LLM-based reasoning. We first examine the architectural foundations of world models, including latent representation learning, dynamics modeling, and imagination-based planning. Building on these core capabilities, we illustrate their proactive applications across EGI scenarios such as vehicular networks, unmanned aerial vehicle (UAV) networks, the Internet of Things (IoT) systems, and network functions virtualization, thereby highlighting how they can enhance optimization under latency, energy, and privacy constraints. We then explore their synergy with foundation models and digital twins, positioning world models as the cognitive backbone of EGI. Finally, we highlight open challenges, such as safety guarantees, efficient training, and constrained deployment, and outline future research directions. This survey provides both a conceptual foundation and a practical roadmap for realizing the next generation of intelligent, autonomous edge systems.
Key Findings
1
Major open challenges include safety guarantees, efficient training, and deployment under constrained edge resources.
2
The paper positions world models as a cognitive backbone that complements agentic AI, large language models, foundation models, and digital twins at the edge.
3
The survey analyzes world-model foundations including latent representation learning, dynamics modeling, and imagination-based multi-step planning.
4
World models can proactively support optimization in vehicular, UAV, IoT, and network-functions-virtualization scenarios under latency, energy, and privacy constraints.
5
World models extend edge general intelligence beyond language-only reasoning by simulating physical dynamics, uncertainty, and future trajectories.
Research Object
world-model-powered agentic artificial intelligence systems for Edge General Intelligence in wireless edge environments
Research Subject
the use of world models to enable proactive perception, prediction, uncertainty-aware multi-step planning, and optimization under latency, energy, and privacy constraints
Publication Details
Publication Date
2026-01-01
Journal
Publisher
ISSN
Cited by
31
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai14
Exploiting Generative AI to Scale up Intelligent Tutoring Systems2023
LLaMA: Open and Efficient Foundation Language Models2023
Generative adversarial networks2020
Generative Adversarial Networks: An Overview2018
GPT-4 Technical Report2023
A Survey on Digital Twin: Definitions, Characteristics, Applications, and Design Implications2019
Edge Intelligence: The Confluence of Edge Computing and Artificial Intelligence2020
Deep learning, reinforcement learning, and world models2022
GPT (Generative Pre-Trained Transformer)— A Comprehensive Review on Enabling Technologies, Potential Applications, Emerging Challenges, and Future Directions2024
AI Agents vs. Agentic AI: A Conceptual taxonomy, applications and challenges2025
AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges2025
Toward Edge General Intelligence With Multiple-Large Language Model (Multi-LLM): Architecture, Trust, and Orchestration2025
A Comprehensive Survey of Large AI Models for Future Communications: Foundations, Applications, and Challenges2026
From Large AI Models to Agentic AI: A Tutorial on Future Intelligent Communications2026