Towards Agentic AI at the Edge: Challenges and Opportunities

Speaker:  Shiqiang Wang – Exeter, United Kingdom
Topic(s):  Artificial Intelligence, Machine Learning, Computer Vision, Natural language processing

Abstract

Agentic AI systems that can reason, plan, and act with tools are becoming a promising paradigm for real world applications, especially at the edge where low latency, privacy, and resilience are critical. However, edge environments impose strict constraints on compute, memory, and reliability, making it challenging to achieve high quality outcomes. In this talk, I will present a perspective on enabling agentic AI at the edge by integrating insights from recent benchmarking and prior work on model selection and routing. Our study shows that agentic performance does not scale simply with model size and instead depends on the interaction between models, tools, and task domains, with non steady scaling trends and distinct failure patterns. Building on this, I will discuss approaches for cost optimal model routing with service guarantees and adaptive inference across both local and cloud nodes, which together help balance quality, latency, and cost. I will conclude by outlining key challenges and opportunities in moving toward robust agentic systems through workload aware model selection and system level co-design.

About this Lecture

Number of Slides:  30
Duration:  60 minutes
Languages Available:  English
Last Updated:  12/05/2026

Request this Lecture

To request this particular lecture, please complete this online form.

Request a Tour

To request a tour with this speaker, please complete this online form.

All requests will be sent to ACM headquarters for review.