The paper proposes a Multi-Agentic AI framework to enable fairness‑aware and accelerated inference of large, heterogeneous multi‑modal language models on mobile edge networks. It introduces a Global Planning Agent, a Prompt Scheduling Agent, and multiple on‑node LM Deployment Agents that jointly optimize prompt routing and model deployment using natural language reasoning over telemetry and historical data. Experiments on a city‑wide testbed show a 42.9% reduction in end‑to‑end latency versus a state‑of‑the‑art baseline and an 80.6% reduction versus a full‑activation baseline, while preserving high fairness (Jain's index 0.925).
By Haiyuan Li, Hari Madhukumar, Shuangyi Yan, Yulei Wu, Dimitra Simeonidou
The paper introduces a dynamic framework for partitioning neural network layers across a heterogeneous edge‑cloud continuum, adapting to runtime changes in network conditions and device capabilities. It profiles models at startup, measures link quality, and periodically re‑evaluates the partitioning to optimize performance. Experiments on a Raspberry Pi, laptop, and desktop using VGG16, AlexNet, and MobileNetV2 demonstrate energy savings of 27.09–35.82% and latency reductions of 6.34–22.92% over static partitioning.
By Akuen Akoi Deng, Eimantas Butkus, Alfreds Lapkovskis, Praveen Kumar Donta
The paper introduces a partition-aware scheduling framework for mobile inference on heterogeneous platforms that combines mobile GPUs and multiple CPU core clusters. It jointly optimizes operator partitioning, device assignment, and execution order for static DAGs of operators, such as those in CNNs or vision transformers. An online iterative search approach decomposes large DAGs into stages, targets critical operators, and uses latency predictors to avoid exhaustive profiling, achieving near‑optimal latency with minimal scheduling overhead.
By Zhuojin Li, Marco Paolieri, Leana Golubchik
MANE is a distributed inference framework that uses a multi‑path tail architecture to allow dynamic accuracy–throughput trade‑offs during edge onloading of deep neural networks. It introduces a novel multi‑path model, a three‑stage training scheme with Joint Head Network Distillation loss, and a hysteresis‑based scheduler with an equitable device‑fallback policy. The system achieves over 80% SLO satisfaction and 6pp higher accuracy than on‑device alternatives while supporting up to 40 concurrent devices.
By Sokratis Nikolaidis, Stylianos I. Venieris, Leonidas Malachias, Iakovos S. Venieris
arXiv:2605. 23809v2 Announce Type: replace-cross Abstract: The Open Radio Access Network (O-RAN) architecture allows AI to be embedded directly into the RAN through modular xApps and rApps, yet creating these applications collecting data, training models, writing code, and deploying them safely remains slow and largely manual.
By Seyed Bagher Hashemi Natanzi, Pranshav Gajjar, Bo Tang, Vijay K. Shah
arXiv:2610.14324v1 Announce Type: cross
Abstract: Foundation models like V-JEPA are increasingly deployed across a heterogeneous edge-cloud continuum spanning smart glasses, phones, robots, and serve...
By Anxhelo Diko, Jieyu Lin, Stefano Ambrogio, Ziyun Li, Mahmoud Assran, Th\'eo Moutakanni, Barbara De Salvo, Chiao Liu
arXiv:2509. 23248v3 Announce Type: replace Abstract: The rapid advancement of large language models (LLMs) has enabled an emergence of agentic artificial intelligence (AI) with powerful reasoning and autonomous decision-making capabilities.
By Mingyi Luo, Ruichen Zhang, Xiangwang Hou, Jun Du, Chunxiao Jiang, Yong Ren, Shiwen Mao
arXiv:2512. 08211v2 Announce Type: replace Abstract: Large language models (LLMs) are moving from cloud-centric services toward on-device embedded AI, where models interact with private, longitudinal signals sensed from users and their physical environments.
By Jiaxiang Geng, Lunyu Zhao, Yiyi Lu, Bing Luo
arXiv:2606. 29518v1 Announce Type: cross Abstract: With the widespread adoption of AI in various IoT scenarios such as smart sensing and processing, AI chips have become a common component at the edge.
By Yihan Wang, Huiru Yan, Luxin Zhang, Long Cheng, Weiwei Chen, Ying Wang, Lei Zhang, Cheng Liu, Huawei Li
arXiv:2607. 16930v1 Announce Type: cross Abstract: Throughput prediction is foundational for artificial intelligence-driven 6G resource orchestration.
By Muhammad Kabeer, Rosdiadee Nordin, Nadiva Nuriftitah, Sian Lun Lau
arXiv:2603. 16867v2 Announce Type: replace Abstract: Large language models (LLMs) with chain-of-thought reasoning achieve state-of-the-art performance across complex problem-solving tasks, but their verbose reasoning traces and large context requirements make them impractical for edge deployment.
By Yelysei Bondarenko, Thomas Hehn, Rob Hesselink, Romain Lepert, Fabio Valerio Massoli, Evgeny Mironov, Leyla Mirvakhabova, Tribhuvanesh Orekondy, Spyridon Stasis, Andrey Kuzmin, Anna Kuzina, Markus Nagel, Ankita Nayak, Corrado Rainone, Ork de Rooij, Paul N Whatmough, Arash Behboodi, Babak Ehteshami Bejnordi
CellTwin, also known as NeuralEmu, is a machine‑learning‑based emulation framework that learns 5G scheduler behavior from high‑resolution network telemetry. It predicts resource block allocations and modulation schemes for multiple clients, reconstructs background traffic patterns, and runs as a high‑performance Linux middlebox. Compared to existing tools, it reduces emulation error by up to 57% for key real‑time applications such as web‑page load, WebRTC, and cloud gaming.
By Haoran Wan, Yaxiong Xie, Kyle Jamieson