Agentic Driving Coach: Robustness and Determinism of Agentic AI-Powered Human-in-the-Loop Cyber-Physical Systems
For developers of human-in-the-loop cyber-physical systems, this work tackles the urgent issue of uncontrollable nondeterminism caused by unpredictable human and AI behavior, but the solution is preliminary and domain-specific.
The paper addresses the challenge of nondeterminism in agentic AI-powered human-in-the-loop cyber-physical systems by proposing a reactor-model-of-computation approach using the Lingua Franca framework. It identifies practical challenges in reintroducing determinism through a driving coach case study.
Foundation models, including large language models (LLMs), are increasingly used for human-in-the-loop (HITL) cyber-physical systems (CPS) because foundation model-based AI agents can potentially interact with both the physical environments and human users. However, the unpredictable behavior of human users and AI agents, in addition to the dynamically changing physical environments, leads to uncontrollable nondeterminism. To address this urgent challenge of enabling agentic AI-powered HITL CPS, we propose a reactor-model-of-computation (MoC)-based approach, realized by the open-source Lingua Franca (LF) framework. We also carry out a concrete case study using the agentic driving coach as an application of HITL CPS. By evaluating the LF-based agentic HITL CPS, we identify practical challenges in reintroducing determinism into such agentic HITL CPS and present pathways to address them.