Practical Adoption Challenges of ML for Systems
Tuesday, September 29, 2026 – co-located with SOSP 2026 (Prague, Czechia)
Embedded Files
Workshop Overview
Using AI for improving computer systems has seen a significant amount of work both in academia and industry, spanning classic machine learning techniques, Generative AI models, and more recently Agentic AI systems. Together, these approaches create new opportunities for improving scheduling, resource management, debugging, performance tuning, configuration management, cloud operations, databases, networks, storage systems, and other parts of the systems stack. However, deployed uses of such techniques remain rare. While many published works in this space focus on solving the underlying learning, reasoning, or planning problems, we find that some of the most critical obstacles to deploying AI for Systems in practice come from systems aspects, such as feature and prompt stability, reliability, availability, integration into rollout and operations processes, verification, safety guarantees, guardrails for autonomous or semi-autonomous actions, feedback loops introduced by learning or agent behavior, debuggability, observability, and explainability.
During this workshop, we will have paper presentations and invited talks with the aim to foster collaboration between systems practitioners, AI practitioners, and academic researchers by providing a venue where real-world deployment challenges and related research work are discussed. We believe that starting this conversation between the academic and industrial research communities will facilitate the adoption of AI for Systems research in production systems, and will provide the academic community with access to new research problems that exist in real-world deployments but have received less attention in the academic community.
To this end, we invite position papers that explore new challenges and design spaces, short papers that describe completed or early-stage work, and abstracts that summarize works published in the past two years in the broad area of challenges associated with using classic ML, Generative AI, and Agentic AI in computer systems. A paper accepted to PACMI would not preclude its future publication at a major conference. Accepted papers will have the option to be included in ACM proceedings. For more details about submissions, please refer to the Call for Papers.
Important Dates (AoE)
Paper submissions due: July 11, 2026
Notification to authors: August 5, 2026
Final version due: August 19, 2026
Page updated
Google Sites
Report abuse