Date: Oct-20, 2026

Location: Room 3, St Raphael Resort

Session 1:    9:00 ~ 10:30

Chair: Xiao-Yi Zhang

• Opening -- 9:00 ~ 9:10 (10 min)

• Keynote I:  Automatic repair of advanced software systems: from AI-enabled to quantum systems-- 9:10 ~ 10:30 (1h20min) 

Paolo Arcaini (Simula, Norway)

Morning Coffee Break 10:30 ~ 11:00

Session 2:  11:00 ~12:30

Chair: Xiao-Yi Zhang

• A Comparative Empirical Study of LLM-Based Test Generation Methods for Competitive Programming -- 11:00 ~ 11:20 (20min)

Ning Shi, Hexiang Xu, Dongxu Wang, Jiajun Zhou, and Ying Shang 

• From Safety Documentation to Safety Knowledge Support: An Evidence-Grounded LLM Framework for Medical Devices  -- 11:20 ~ 11:40 (20min)

Tuhinangshu Gangopadhyay, Rasmus Adler, Peter Liggesmeyer, and Jan Reich

• SenWorld: A Digital-Twin Simulation for Generating Context-Rich Evaluation Data -- 11:40 ~ 12:00 (20min)

Zenghui Zhou, Xiaoyang Li, Xiaoxuan Qiao, Zhilang Wei, and Tianming Lei

• Neuro-Symbolic Protocol Guardian for Secure Multi-Agent LLM Systems -- 12:00 ~ 12:20 (20min)

Shutong Zhang

• (Short) A Preliminary Evaluation of the Non-determinism of VLAs for Robotic Tasks-- 12:20 ~ 12:30 (10min)

Deyun Lyu, Paolo Arcaini, Fuyuki Ishikawa, and Gilles Perrouin

Lunch Break 12:30 -- 14:00

Session 3:  14:00 ~15:30

Chair: Xiao-Yi Zhang

• Invited Talk: AgentOps: Toward Reliable Operations for AI Agent Systems -- 14:00 ~ 14:35 (35 min)

Wenwei Gu  (Nankai University, China)

• Component-Level Reliability Assessment of Graph Neural Networks under Soft Errors 14:35 ~ 14:55 (20 min)

Sanem Arslan, Erkut Dönmez and Mert Muslu

• A Structured Knowledge Base for LLM-Based Test Case Generation in Online Judges -- 14:55 ~ 15:15 (20 min)

Jiajun Zhou, Daguang Jiang, Hexiang Xu, Yong Liu and Ning Shi

• (Short) Phoenix: Parallel Event-Driven Simulation in PeerSim for Intelligent Workloads -- 15:15 ~ 15:25 (10 min)

Susana Marques, Cláudia Brito and Fábio Coelho

• (Fast Abstract) Pinned Release Replays Expose Diagnostic Changes in AI Instrumentation -- 15:25 ~ 15:30 (5min)

Krishna Chaitanya Balusu

Afternoon Coffee Break 15:30 ~ 16:00

Session 4:  16:00 ~17:30

Chair: Wenwei Gu

• Operational Reliability Patterns in AI Personalization Serving Infrastructure: Practitioner-Grounded Hypotheses and a Clean-Room Reproduction Study -- 16:00 ~ 16:20 (20min)

Srinivas Kalyan Yellanki and Nicholas Piazza

• LLM-Driven Generation of Complex Multi-Vehicle Interaction Scenarios for Autonomous Driving -- 16:20 ~ 16:40 (20min)

Yashuo Chen, Xu Gao and Xiao-Yi Zhang

• Characterizing the Diagnosability of Spectrum-Based Fault Localisation via Spectrum Distribution Patterns -- 16:40 ~ 17:00 (20min)

Yan Zheng, Xiao-Yi Zhang and Yong Liu

• Trustworthy-by-Design LLM-Based Systems: A Specification Method Driven by Intended Purpose and Operational Domain -- 17:00 ~ 17:20 (20 min)

Afef Awadid

• Closing  17:20 ~ 17:30 (10 min)