Hybrid Stackelberg Game and Diffusion-based Auction for Two-tier Agentic AI Task Offloading in Internet of Agents

2025-11-26

AI Summary

In the Internet of Agents (IoA), resource-constrained wireless agents (WAs) and easily overloaded fixed agents (FAs) severely degrade task offloading efficiency. To address this, we propose a two-tier collaborative offloading architecture: the first tier enables dynamic offloading between WAs and ground-based agents (mobile or fixed agents, MAs/FAs); the second tier supports elastic task migration from overloaded FAs to aerial agents (AAs). Our approach innovatively integrates a multi-leader–multi-follower Stackelberg game with a double Dutch auction mechanism, augmented by a diffusion-model-based deep reinforcement learning framework for joint resource pricing and scheduling optimization. Experimental results demonstrate that our framework significantly outperforms state-of-the-art methods in task completion rate, resource utilization, and end-to-end latency—thereby enhancing both the overall performance and robustness of heterogeneous agent collaborative inference.

Technology Category

• Multiagent Systems: Mechanism Design
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Search and Optimization: Learning to Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

The Internet of Agents (IoA) is rapidly gaining prominence as a foundational architecture for interconnected intelligent systems, designed to facilitate seamless discovery, communication, and collaborative reasoning among a vast network of Artificial Intelligence (AI) agents. Powered by Large Language and Vision-Language Models, IoA enables the development of interactive, rational agents capable of complex cooperation, moving far beyond traditional isolated models. IoA involves physical entities, i.e., Wireless Agents (WAs) with limited onboard resources, which need to offload their compute-intensive agentic AI services to nearby servers. Such servers can be Mobile Agents (MAs), e.g., vehicle agents, or Fixed Agents (FAs), e.g., end-side units agents. Given their fixed geographical locations and stable connectivity, FAs can serve as reliable communication gateways and task aggregation points. This stability allows them to effectively coordinate with and offload to an Aerial Agent (AA) tier, which has an advantage not affordable for highly mobile MAs with dynamic connectivity limitations. As such, we propose a two-tier optimization approach. The first tier employs a multi-leader multi-follower Stackelberg game. In the game, MAs and FAs act as the leaders who set resource prices. WAs are the followers to determine task offloading ratios. However, when FAs become overloaded, they can further offload tasks to available aerial resources. Therefore, the second tier introduces a Double Dutch Auction model where overloaded FAs act as the buyers to request resources, and AAs serve as the sellers for resource provision. We then develop a diffusion-based Deep Reinforcement Learning algorithm to solve the model. Numerical results demonstrate the superiority of our proposed scheme in facilitating task offloading.

Problem

• Optimizes task offloading from wireless to aerial agents via game theory
• Addresses resource allocation in multi-tier Internet of Agents systems
• Solves overload management using auction mechanisms and deep reinforcement learning

Innovation

• Hybrid Stackelberg game for resource pricing and offloading
• Double Dutch Auction for aerial resource allocation
• Diffusion-based Deep Reinforcement Learning for model optimization