The paper surveys energy efficiency strategies for Agentic AI inference by proposing a new accounting framework and taxonomy that spans model simplification, computation control, input optimization, and cross-layer co-design with wireless networks.
Proceedings of the Workshop on Edge and Mobile Foundation Models , pages =
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
citing papers explorer
-
Networking-Aware Energy Efficiency in Agentic AI Inference: A Survey
The paper surveys energy efficiency strategies for Agentic AI inference by proposing a new accounting framework and taxonomy that spans model simplification, computation control, input optimization, and cross-layer co-design with wireless networks.
- PipeSD: An Efficient Cloud-Edge Collaborative Pipeline Inference Framework with Speculative Decoding