# Agentic Driving Coach: Robustness and Determinism of Agentic AI-Powered Human-in-the-Loop Cyber-Physical Systems

arXiv: https://arxiv.org/abs/2604.11705 · HTML: https://mlsanity.com/paper/2604.11705/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Large language models for driving, one of 9 directions in End-to-end autonomous driving.
- Builds on 18 of its 42 references that are in the map.
- First posted on arXiv 13 Apr 2026.

## Placed in

- End-to-end autonomous driving / [Large language models for driving](https://mlsanity.com/driving/large-language-models-for-driving/)
- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 18 of 18)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection](https://mlsanity.com/paper/2403.03507/) (2024)
- [A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems](https://mlsanity.com/paper/2508.07407/) (2025)
- [Drive Like a Human: Rethinking Autonomous Driving with Large Language Models](https://mlsanity.com/paper/2307.07162/) (2023)
- [Waymo Public Road Safety Performance Data](https://mlsanity.com/paper/2011.00038/) (2020)
- [An LLM-Based Digital Twin for Optimizing Human-in-the Loop Systems](https://mlsanity.com/paper/2403.16809/) (2024)
- [Safe LLM-Controlled Robots with Formal Guarantees via Reachability Analysis](https://mlsanity.com/paper/2503.03911/) (2025)
- [Exploring the Capabilities of LLMs for IMU-based Fine-grained Human Activity Understanding](https://mlsanity.com/paper/2504.02878/) (2025)
- [On the Efficiency and Robustness of Vibration-based Foundation Models for IoT Sensing: A Case Study](https://mlsanity.com/paper/2404.02461/) (2024)
- [CPS-LLM: Large Language Model based Safe Usage Plan Generator for Human-in-the-Loop Human-in-the-Plant Cyber-Physical System](https://mlsanity.com/paper/2405.11458/) (2024)
- [Personalizing Large Language Models using Retrieval Augmented Generation and Knowledge Graph](https://mlsanity.com/paper/2505.09945/) (2025)
- [DURA-CPS: A Multi-Role Orchestrator for Dependability Assurance in LLM-Enabled Cyber-Physical Systems](https://mlsanity.com/paper/2506.06381/) (2025)
- [Achieving Determinism in Adaptive AUTOSAR](https://mlsanity.com/paper/1912.01367/) (2019)
- [Toward Foundation Models for Online Complex Event Detection in CPS-IoT: A Case Study](https://mlsanity.com/paper/2503.12282/) (2025)
- [Cyber Physical Games](https://mlsanity.com/paper/2407.05817/) (2024)
- [Who is Responsible? Explaining Safety Violations in Multi-Agent Cyber-Physical Systems](https://mlsanity.com/paper/2410.20288/) (2024)

## Abstract (arXiv)

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.