Agentic Driving Coach: Robustness and Determinism of Agentic AI-Powered Human-in-the-Loop Cyber-Physical Systems
On the map: End-to-end autonomous driving → Large language models for driving
also in 1 more
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.
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.
Builds on
18 of 42 references.
Closest ancestors · 1
Same direction, newest first
Other references · 17
- 2024The Llama 3 Herd of Modelscited by 14,715
- 2021On the Opportunities and Risks of Foundation Modelscited by 4,033
- 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,191
- 2024GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projectioncited by 463
- 2025A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systemscited by 183
- 2020Waymo Public Road Safety Performance Datacited by 24
- 2024An LLM-Based Digital Twin for Optimizing Human-in-the Loop Systemscited by 13
- 2025Safe LLM-Controlled Robots with Formal Guarantees via Reachability Analysiscited by 9
- 2025Exploring the Capabilities of LLMs for IMU-based Fine-grained Human Activity Understandingcited by 5
- 2024On the Efficiency and Robustness of Vibration-based Foundation Models for IoT Sensing: A Case Studycited by 4
- 2024CPS-LLM: Large Language Model based Safe Usage Plan Generator for Human-in-the-Loop Human-in-the-Plant Cyber-Physical Systemcited by 4
- 2025Personalizing Large Language Models using Retrieval Augmented Generation and Knowledge Graphcited by 3
5 more
- 2025DURA-CPS: A Multi-Role Orchestrator for Dependability Assurance in LLM-Enabled Cyber-Physical Systemscited by 3
- 2019Achieving Determinism in Adaptive AUTOSARcited by 2
- 2025Toward Foundation Models for Online Complex Event Detection in CPS-IoT: A Case Studycited by 2
- 2024Cyber Physical Gamescited by 1
- 2024Who is Responsible? Explaining Safety Violations in Multi-Agent Cyber-Physical Systemscited by 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026Agentic Artificial Intelligence (AI): Architectures, Taxonomies, and Evaluation of Large Language Model Agents
- 2026From Digital to Physical: Digital Agents as Autonomous Coaches for Physical Intelligence
- 2026The Path Ahead for Agentic AI: Challenges and Opportunities
- 2025Agentic Physical AI toward a Domain-Specific Foundation Model for Energy Systems: A Case Study on Nuclear Reactor Control
- 2024Practical Considerations for Agentic LLM Systems
- 2025Architecting Human-AI Cocreation for Technical Services -- Interaction Modes and Contingency Factors
- 2025Detailed balance in large language model-driven agents
- 2025Agentic AI Frameworks: Architectures, Protocols, and Design Challenges