Shaohua Cao

Zijun Zhan, Yaxian Dong, Yuqing Hu et al.

Integrating low-light image enhancement techniques, in which diffusion-based AI-generated content (AIGC) models are promising, is necessary to enhance nighttime teleoperation. Remarkably, the AIGC model is computation-intensive, thus necessitating the allocation of AIGC tasks to edge servers with ample computational resources. Given the distinct cost of the AIGC model trained with varying-sized datasets and AIGC tasks possessing disparate demand, it is imperative to formulate a differential pricing strategy to optimize the utility of teleoperators and edge servers concurrently. Nonetheless, the pricing strategy formulation is under information asymmetry, i.e., the demand (e.g., the difficulty level of AIGC tasks and their distribution) of AIGC tasks is hidden information to edge servers. Additionally, manually assessing the difficulty level of AIGC tasks is tedious and unnecessary for teleoperators. To this end, we devise a framework of AIGC task allocation assisted by the Vision Language Model (VLM)-empowered contract theory, which includes two components: VLM-empowered difficulty assessment and contract theory-assisted AIGC task allocation. The first component enables automatic and accurate AIGC task difficulty assessment. The second component is capable of formulating the pricing strategy for edge servers under information asymmetry, thereby optimizing the utility of both edge servers and teleoperators. The simulation results demonstrated that our proposed framework can improve the average utility of teleoperators and edge servers by 10.88~12.43% and 1.4~2.17%, respectively. Code and data are available at https://github.com/ZiJun0819/VLM-Contract-Theory.

Zijun Zhan, Yaxian Dong, Daniel Mawunyo Doe et al.

Artificial intelligence radio access networks (AI-RANs) are a promising architecture for bolstering the prosperity of the edge AI ecosystem. A well-designed incentive mechanism can further ensure the sustainable development of this ecosystem. However, incentive mechanism design faces two major challenges: 1) information asymmetry, where AI-RAN operators have only partial knowledge of AI users' utility functions, and 2) competition, as multiple AI-RAN operators coexist in real-world markets. Remarkably, chaotic and adversarial competition might compromise AI-RAN operators' utility. To this end, we develop a matching-with-contracts framework for incentive mechanism design in AI-RAN service markets. The framework extends the static matching-with-contracts model by jointly characterizing the contract design of multiple competitive operators, user-operator matching, and dynamic evolution of the market state. Specifically, the incentive mechanism offered by each AI-RAN operator takes the form of a contract menu, where each contract item consists of an AI service latency agreement and a corresponding price. We model the AI service process as three independent queues and characterize the violation probability of the latency agreement using queueing theory and the Chernoff bound. To derive an effective incentive mechanism, we further propose a mixed stable matching-with-contracts algorithm that jointly updates user-side matching decisions and operator-side contract menus. Simulation results for a teleoperation-oriented AIGC service demonstrate the effectiveness and robustness of the proposed method. Compared with benchmark schemes, our method improves the total utility of AI-RAN operators by at least 56.8\% under representative settings.

Shanyv Liu, Xuyang Yuan, Tao Chen et al.

Graph-based Multi-Agent Systems (MAS) enable complex cyclic workflows but suffer from inefficient static model allocation, where deploying strong models uniformly wastes computation on trivial sub-tasks. We propose CASTER (Context-Aware Strategy for Task Efficient Routing), a lightweight router for dynamic model selection in graph-based MAS. CASTER employs a Dual-Signal Router that combines semantic embeddings with structural meta-features to estimate task difficulty. During training, the router self-optimizes through a Cold Start to Iterative Evolution paradigm, learning from its own routing failures via on-policy negative feedback. Experiments using LLM-as-a-Judge evaluation across Software Engineering, Data Analysis, Scientific Discovery, and Cybersecurity demonstrate that CASTER reduces inference cost by up to 72.4% compared to strong-model baselines while matching their success rates, and consistently outperforms both heuristic routing and FrugalGPT across all domains.