Program

8:50-9:00 Workshop opening

9:00-10:00 Invited talks

●       Jennifer Horkoff (University of Gothenburg/Chalmers University of Technology) - Requirements Engineering for Generative AI Systems

●       Son Tong (Siemens) - Industrial Agentic AI Workflow: Practice and Research 

10:00-10:30 Contributed Talks (A1): Reliable LLM Reasoning, Prompting, and Deployment

·       Policy-as-Logic for Robust Reasoning over Rules
Rahul Nair, Bastian Lipka, Elizabeth M. Daly

·       Safety-Prefix Pinning for Production KV-Cache Quantization: Measurement, Mechanism, and a Multilingual Defense
Hikaru Matsuoka

10:30-11:00 Coffee break

11:00-11:30 Contributed Talks (A2): Reliable LLM Reasoning, Prompting, and Deployment

·       DocConf: Document-Grounded Confidence Estimation for Robust LLM Field Extraction
Nitesh Kumar

·       From Monolithic to Modular: Segment-level Automatic Prompt Optimization
Kulin Nikita, Zhuravlev Viktor, Khairullin Artur, Sergey Muravyov, Ilya Makarov, Daniil Sukhorukov

11:30-12:30 Invited talks

●   Markus Rickert (Uni. Bamberg) - From Process Descriptions to Robot Behavior: Intuitive Instruction for Small-Lot Production

●      Luca Marzari (TU Vienna) - From Classical to Scalable Verification of Neural Networks: Challenges and Opportunities in Reinforcement Learning

12:30-14:00 Lunch

14:00-15:00 Contributed Talks (B): Robust Agents, Scenario Generation, and Compositional Testing

·       Robust Translation of Natural Language into Traffic Sequence Charts and Co-Simulation with Human Driver Models

Julian Müller, Jan-Patrick Osterloh, Eike Möhlmann

·   GUI Agent: Guided Exploration of User-Sensitive Screens

Aradhana Nayak, Mussadiq Nazeer, Peng Wang, Feng Liu

·   Uncertainty-Aware Retrieval for Robust Scenario Composition: A GFlowNet–RAG Framework with Subset-Simulation Calibration

Yingjie Wang, Xiangyu Yin, Julian Müller

·       TestNav: Pareto-Guided Search for Compositional Robustness Testing

Arooj Arif, Alexandros Koliousis, Tobias Hartung, Elena Botoeva

15:00-15:30 Coffee break

15:30-16:00 Invited Talk

●       Jan Kretinsky (TU Munich and Masaryk University) - Explainable Runtime Monitoring of AI-aided CPS

16:00-17:30 Contributed Talks (C): Domain-Specific Trustworthiness and Robust Decision-Making

·       Clinically Aware Synthetic Image Generation for Concept Coverage in Chest X-ray Models
Amy Rafferty, Rishi Ramaesh, Ajitha Rajan

·       Distinguishing AI-Generated Music from Edited Audio as a Hard-Negative Robustness Task
Alexandru-Stefan Morosanu, Valerian Cecan, Laura Erhan, Stefan Daniel Achirei

·       Trustworthiness of LLMs in Cross-Lingual Clinical Summarization: An Empirical Study on Indian Languages

Kunwar Zaid, Amit Sangroya, Jyotsana Khatri, Vikas Kumar

·       BIEV: A Differentiable Framework for Precise Property Manipulation of Biological Entities
Zhiguo Tao, He Zhihua

·       Quantifying Risk Under Evolving Uncertainty: Belief-Dependent Robustness for Safe Sequential Decision Making

Deep Kumar Ganguly, Jan Kretinsky

·       Monitoring with Guarantees via Randomized Smoothing
Diganta Mukhopadhyay, Jan Kretinsky