Smart Adaptive Computing Across the Continuum: LLMs in IoT-Edge-Cloud Resource Management

arXiv:2609.09348 · cs.DC, cs.AI, cs.MA · Submitted 2026-09-08 · Read on arXiv

cs.DC, cs.AI, cs.MA

Submitted: 2026-09-08

Updated: 2026-09-08

Comments: This is the Accepted Manuscript, after peer review, not the Version of Record; no post-acceptance changes. Presented at FRAME 2026 (Euro-Par 2026). Subject to Springer's AM terms of use: https://www.springernature.com/gp/open-research/policies/accepted-manuscript-terms

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Abstraction — 1× in this paper · explained in 1 episode
• Deep Reinforcement Learning — 1× in this paper · explained in 2 episodes
• Deep Reinforcement Learning (DRL) — 1× in this paper · explained in 2 episodes
• LLM Orchestrator — 1× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes

Related papers

• iScheduler: Reinforcement Learning-Driven Continual Optimization for Large-Scale Resource Investment Problems
• SAMM: Sharded Automated Market Maker
• InferScale: GPU-Native KV Injection for Personalized LLM Serving
• Vigil: Accountable Liveness against Selective Silence
• Steelhead: Interleaving Partially Synchronous and Asynchronous Commit Rules on a Shared DAG
• Pushing CPU Speech Synthesis to the Wall: Extreme Inference Tuning under Serverless Architecture and Billing