{"id":4000,"date":"2026-05-14T13:23:31","date_gmt":"2026-05-14T12:23:31","guid":{"rendered":"https:\/\/blogs.qub.ac.uk\/dipsa\/?p=4000"},"modified":"2026-05-14T13:26:02","modified_gmt":"2026-05-14T12:26:02","slug":"invited-talk-prof-shiqiang-wang-towards-agentic-ai-at-the-edge-challenges-and-opportunities","status":"publish","type":"post","link":"https:\/\/blogs.qub.ac.uk\/dipsa\/invited-talk-prof-shiqiang-wang-towards-agentic-ai-at-the-edge-challenges-and-opportunities\/","title":{"rendered":"Invited Talk – Prof Shiqiang Wang – Towards Agentic AI at the Edge: Challenges and Opportunities"},"content":{"rendered":"\n
\n
\"\"<\/figure>\n\n\n\n
\"\"<\/figure>\n\n\n\n
\"\"<\/figure>\n\n\n\n
\"\"<\/figure>\n<\/figure>\n\n\n\n

Abstract<\/h3>\n\n\n\n

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 such as MESS+ for cost optimal model routing with service guarantees and TMO for 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.<\/p>\n\n\n\n

Bio<\/h3>\n\n\n\n

Shiqiang Wang is a Professor of Artificial Intelligence in the Department of Computer Science, University of Exeter, United Kingdom. He was a researcher at IBM T. J. Watson Research Center, NY, United States until Oct. 2025. He received his Ph.D. from Imperial College London, United Kingdom, in 2015. His research focuses on the intersection of artificial intelligence (AI), distributed computing, and optimization, with a broad range of applications including large language models (LLMs), agentic AI, efficient model training and inference, and AI in distributed systems. He has made foundational contributions to edge computing and federated learning that generated both academic and industrial impact. Dr. Wang served as an associate editor of the IEEE Transactions on Mobile Computing, IEEE Transactions on Parallel and Distributed Systems, and IEEE Transactions on Computational Social Systems. He also served as an area chair of major AI and machine learning conferences, including AAAI, ICLR, ICML, and NeurIPS. He received the IEEE Communications Society (ComSoc) Leonard G. Abraham Prize in 2021, IEEE ComSoc Best Young Professional Award in Industry in 2021, Best Paper Runner-Up of ACM MobiHoc 2025, IBM Outstanding Technical Achievement Awards (OTAA) in 2019, 2021, 2022, and 2023, multiple Invention Achievement Awards from IBM since 2016, and Best Student Paper Award of the Network and Information Sciences International Technology Alliance (NIS-ITA) in 2015. He is an IEEE Fellow (Class of 2026) and a member of ACM and ELLIS. <\/p>\n\n\n\n

More details are available in his homepage<\/a>.<\/p>\n","protected":false},"excerpt":{"rendered":"

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, […]<\/p>\n","protected":false},"author":1149,"featured_media":4004,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_jetpack_memberships_contains_paid_content":false,"footnotes":""},"categories":[1],"tags":[],"class_list":{"0":"post-4000","1":"post","2":"type-post","3":"status-publish","4":"format-standard","5":"has-post-thumbnail","7":"category-uncategorised","8":"czr-hentry"},"jetpack_featured_media_url":"https:\/\/blogs.qub.ac.uk\/dipsa\/wp-content\/uploads\/sites\/14\/2026\/05\/shiqiang-1-scaled.jpeg","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/blogs.qub.ac.uk\/dipsa\/wp-json\/wp\/v2\/posts\/4000","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/blogs.qub.ac.uk\/dipsa\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/blogs.qub.ac.uk\/dipsa\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/blogs.qub.ac.uk\/dipsa\/wp-json\/wp\/v2\/users\/1149"}],"replies":[{"embeddable":true,"href":"https:\/\/blogs.qub.ac.uk\/dipsa\/wp-json\/wp\/v2\/comments?post=4000"}],"version-history":[{"count":2,"href":"https:\/\/blogs.qub.ac.uk\/dipsa\/wp-json\/wp\/v2\/posts\/4000\/revisions"}],"predecessor-version":[{"id":4007,"href":"https:\/\/blogs.qub.ac.uk\/dipsa\/wp-json\/wp\/v2\/posts\/4000\/revisions\/4007"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/blogs.qub.ac.uk\/dipsa\/wp-json\/wp\/v2\/media\/4004"}],"wp:attachment":[{"href":"https:\/\/blogs.qub.ac.uk\/dipsa\/wp-json\/wp\/v2\/media?parent=4000"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/blogs.qub.ac.uk\/dipsa\/wp-json\/wp\/v2\/categories?post=4000"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/blogs.qub.ac.uk\/dipsa\/wp-json\/wp\/v2\/tags?post=4000"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}