@inproceedings{iccps2026_logiex,
author = {An, Ziyan and Wang, Xia and Baier, Hendrik and Chen, Zirong and Dubey, Abhishek and Mukhopadhyay, Ayan and Johnson, Taylor T. and Sprinkle, Jonathan and Ma, Meiyi},
title = {LogiEx: Logic-Integrated Explanations for Stochastic Planning in Cyber-Physical Systems},
year = {2026},
booktitle = {Proceedings of the HSCC/ICCPS 2026: 29th ACM International Conference on Hybrid Systems: Computation and Control and 17th ACM/IEEE International Conference on Cyber-Physical Systems},
location = {Saint Malo, France},
abstract = {Human-centered cyber-physical systems (CPS), such as intelligent transportation services, warehouse robotics operated by human supervisors, and healthcare infrastructures involving clinicians and medical staff, increasingly rely on Artificial Intelligence (AI)-driven sequential decision-making under uncertainty. However, the lack of transparent reasoning in these systems limits trust, verifiability, and human oversight. This challenge is particularly acute for planning algorithms like Monte Carlo Tree Search (MCTS), whose stochastic search processes are opaque to engineers and operators. To address this gap, we introduce LogiEx, a logic-integrated framework that combines large language models (LLMs) with formal methods to generate trustworthy explanations for planning behavior. LogiEx transforms free-form user queries into logical statements with templated variables, then verifies whether evidence extracted from the decision process aligns with both the environment state and the constraints of the stochastic planning model. This enables grounded explanations across a wide range of user questions—from factual retrieval to comparative reasoning. LogiEx also supports Human-Guided Search (HuGS), allowing users to pose conditional `what-if'' queries that trigger new, scenario-specific searches, ensuring that humans are not passive observers but active participants who can steer and refine the planning process. We evaluate LogiEx through both quantitative assessments and user studies, finding that it consistently outperforms baselines, achieving up to 7.9 higher semantic similarity (BERTScore) and 1.6 higher factual consistency (FactCC) compared to baseline LLMs, and is the most preferred form of explanation among CPS practitioners.},
keywords = {explainable AI, transit planning, formal logic, large language models, Monte Carlo tree search, knowledge graphs, human-AI interaction},
note = {Acceptance rate: 28\%; Regular Paper; Track: Systems and Applications},
series = {HSCC/ICCPS '26}
}