Guest talk: Xi Zheng "From Probabilistic Testing to Certifiable AI: Large Language Models and Neuro-Symbolic Reasoning for Verifiable Autonomous Systems"

From Probabilistic Testing to Certifiable AI: Large Language Models and Neuro-Symbolic Reasoning for Verifiable Autonomous Systems

Xi Zheng 
Macquarie University, Australia

Abstract: Learning-enabled Cyber-Physical Systems (LE-CPS), such as autonomous vehicles and drones, pose significant challenges for safety assurance due to the unpredictability of deep neural networks. Our FSE’22 and TSE’23 studies exposed critical gaps in industry testing practices, motivating new techniques for test reduction and scenario-based validation in autonomous systems.

This talk highlights two recent vision-led directions. The FSE’24 vision revives model-based testing through Large Language Models (LLMs), already adopted in industry pipelines. Follow-up works in TSE’24 and ICSE’25 extend this to LLM-driven scenario generation and online testing for UAV autolanding.

The FSE’25 vision, NeuroStrata, proposes a neurosymbolic shift from black-box learning to interpretable reasoning, enabling certifiable AI. This vision is now realized in a neurosymbolic perception module under real-world deployment with an Australian drone company, and has gained strong support across European institutions during my recent visit, including Oxford, Paris-Saclay, Hamburg, FSE’25, and CAV’25.

Together, these efforts chart a path toward verifiable, certifiable AI for safety-critical systems.

Bio: A/Prof. Xi Zheng (Macquarie University, Australia) is an ARC Future Fellow (2024–2028) whose research focuses on testing and verification of learning-enabled cyber-physical systems, with applications to autonomous vehicles and UAVs. He has secured over $2.4M in competitive funding and published extensively in top venues such as ICSE, FSE, and TSE. His research outputs have been adopted in industry by partners including Ant Group and UAV companies. Beyond research, he has taken on significant leadership and service roles, serving as TPC Chair (MobiQuitous 2026), OC/TPC member (ICSE 2026, FSE 2026, PerCom 2026, CAV 2025). He also co-founded the TACPS workshop series and is co-organizer of the Shonan Seminar #235 and Dagstuhl Seminar 202501048 (2026) on neurosymbolic AI and LLMs for reliable autonomous systems.

This guest talk is hosted by Assistant Professor Haoye Tian, Department of Computer Science.