The workshop location is Crystal Ballroom A (3F). (More information on the location can be found here.)

Opening remarks (Byung-Gon Chun) 2:00 – 2:05

Session 1: Foundations and Architecture (Chair: Byung-Gon Chun) 2:05 - 2:55
"Foundational Systems for Agentic AI"

  • Useful Agentic AI: A Systems Outlook
    Marquita Ellis (IBM Research); Melissa Pan (UC Berkeley); Jared Quincy Davis (Stanford University); Yuxuan Zhu (University of Illinois at Urbana-Champaign); Riccardo Cogo (Intesa Sanpaolo); Lakshya A Agrawal, Negar Arabzadeh, Xiaoyuan Liu, Huanzhi Mao, Sid Pallerla, Tianneng Shi, Alexander Xiong (UC Berkeley); Alessandro Basile, Emmanuele Lacavalla, Shuyi Yang (Intesa Sanpaolo); Diana Arroyo, Paul Castro (IBM Research); Daniel Kang (University of Illinois at Urbana-Champaign); Joseph Gonzalez, Koushik Sen, Dawn Song, Ion Stoica, Matei Zaharia (UC Berkeley)
  • Toward Systems Foundations for Agentic Exploration
    Jiakai Xu, Tianle Zhou, Eugene Wu, Kostis Kaffes (Columbia University)
  • Supporting Our AI Overlords: Redesigning Data Systems to be Agent-First
    Shu Liu, Soujanya Ponnapalli, Shreya Shankar, Sepanta Zeighami, Alan Zhu, Shubham Agarwal, Ruiqi Chen, Samion Suwito, Shuo Yuan, Ion Stoica, Matei Zaharia (UC Berkeley); Alvin Cheung (University of California, Berkeley); Natacha Crooks (UC Berkeley); Joseph Gonzalez (University of California); Aditya Parameswaran (UC Berkeley)

Break 2:55 - 3:00

Session 2: Resource Management and Optimization (Chair: Jae Wook Lee) 3:00 - 3:55
"Efficient Resource Orchestration for AI Agents"

  • Cortex: Workflow-Aware Resource Pooling and Scheduling for Agentic Serving
    Nikos Pagonas (Columbia University); Yeounoh Chung (Google); Kostis Kaffes (Columbia University); Arvind Krishnamurthy (Google/Univ. of Washington)
  • Tetris: Efficient and Predictive KV Cache Offloading for Agentic and Reasoning Workloads
    Ziji Shi (National University of Singapore, Sea AI Lab); Chaoyi Ruan (National University of Singapore); Penghui Qi, Guangxing Huang, Xinyi Wan, Min Lin (Sea AI Lab); Jialin Li (National University of Singapore)
  • GPU Memory Prediction for Multimodal Model Training
    Jinwoo Jeong, Minchul Kang, Younghun Go, Changyong Shin, Hyunho Lee (Department of Computer Science and Engineering, Korea University); Junho Yoon (KT Corporation); Gyeongsik Yang, Chuck Yoo (Department of Computer Science and Engineering, Korea University)

Break 3:55 – 4:15

Session 3: Deployment, Monitoring, and Learning (Chair: Gyeongin Yu) 4:15 – 5:30
"Operationalizing AI Agents: From Deployment to Continuous Improvement"

  • DMAS-Forge: A Framework for Transparent Deployment of AI Applications as Distributed Systems
    Alessandro Cornacchia (KAUST); Vaastav Anand (Max Planck Institute for Software Systems); Muhammad Bilal (KAUST); Zafar Ayyub Qazi (LUMS & KAUST); Marco Canini (KAUST)
  • Automated Annotation Inference for MCP-based Agents
    Grigoris Ntousakis (Brown University); Julian James Stephen, Michael V. Le (IBM); Sai Sree Laya Chukkapalli, Teryl Taylor, Frederico Araujo (IBM Research)
  • EARL: Efficient Agentic Reinforcement Learning Systems for Large Language Models
    Zheyue Tan, Mustapha Abdullahi, Tuo Shi (Aalto University); Huining Yuan, Zelai Xu, Chao Yu (Tsinghua University); Boxun Li (Infinigence-AI); Bo Zhao (Aalto University)
  • AI Agent observability
    Yusheng Zheng (UC Santa Cruz); Yanpeng Hu (ShanghaiTech University)