Assuring Learning-Enabled Cyber-Physical Systems with Foundation Models: A Neuro-Symbolic Agenda for Testing, Verification, and Runtime Assurance
Authors: Xi Zheng, Ivan Ruchkin, Hong Jin Kang, Tevfik Bultan, Vijay Ganesh, Taylor T. Johnson, Ziyang Li, Lei Ma, Aloysius K. Mok, Daniel Neider, Ruzica Piskac, Nalini Venkatasubramanian, Simon Thompson, Sanjoy Baruah
Organizations: Macquarie University, Australia · University of Florida, USA · University of Sydney, Australia · University of California, Santa Barbara, USA · Georgia Institute of Technology, USA · Vanderbilt University, USA · Johns Hopkins University, USA · The University of Tokyo, Japan · The University of Texas at Austin, USA · TU Dortmund University, Germany · Yale University, USA · University of California, Irvine, USA · TIER IV, Japan · Washington University in St. Louis, USA
Learning-enabled cyber-physical systems (CPS), including autonomous vehicles and UAVs, increasingly incorporate foundation models, yet fragmented assurance practices provide insufficient support for system-level guarantees. We argue that restoring engineering control across stochastic neural, symbolic, and physical boundaries requires a shift from model-centric evaluation to system-level assurance. We introduce the Foundation Model Assurance Stack, connecting three directions: (i) neuro-symbolic architectures that constrain foundation models through explicit symbolic world models, reasoning layers, and interfaces; (ii) semantically grounded, conformance-based testing that combines formal specifications and symbolic world models with foundation-model-assisted specification mining, scenario generation, and test synthesis; and (iii) compositional verification and runtime assurance that target formally tractable components and interfaces through modular contracts, equivalence checking, verified synthesis, uncertainty-aware reasoning, and runtime monitoring and enforcement. Symbolic abstractions establish assurance boundaries between stochastic learning and formal reasoning, connecting testing, verification, and runtime evidence across the system lifecycle. Foundation models serve as constrained assistants whose outputs are independently checked wherever correctness can be formally specified. We identify research challenges in specification engineering, abstraction fidelity, evidence composition, and lifecycle certification, and outline a staged agenda toward trustworthy, deployable, and certifiable learning-enabled CPS.
Figures & tables
Figure 1. Foundation Model Assurance Stack for AI-Enabled CPS. The stack organizes assurance into three complementary pillars: foundation models as assistive components in CPS architectures, testing and validation of AI-enabled systems, and verification and runtime assurance. These pillars are connected by cross-cutting neuro-symbolic integration, including symbolic world models, DSLs and structured representations, contract specifications, and neural–symbolic interfaces. Architecture provides world models, specifications, and interfaces to testing, and contracts, abstractions, and constraints to verification. Testing provides empirical evidence through conformance-based testing, structured scenario generation, DSL-guided test synthesis, LLM-assisted specification mining, and adequacy assessment. Verification and runtime assurance provide formal guarantees through contract verification, interface verification, transformation verification, runtime monitoring, and safety enforcement. At runtime, a Simplex-style resilience layer combines a learning-enabled controller, runtime monitor, safe controller, and shielding or switching mechanism to support operational safety under uncertainty.
Cyber-Physical Systems (CPS) study networked computation and control interacting with physical processes, from factories and power grids to robots and vehicles.
Large Language Models (LLMs), deep learning architectures with typically over 10 billion parameters, have recently begun to be integrated into various cyber-physical systems (CPS) such as robotics, industrial automation, and autopilot systems. The abstract knowledge and reasoning capabilities of LLMs are employed for tasks like planning and navigation. However, a significant challenge arises from the tendency of LLMs to produce "hallucinations" - outputs that are coherent yet factually incorrect or contextually unsuitable. This characteristic can lead to undesirable or unsafe actions in the CPS. Therefore, our research focuses on assuring the LLM-enabled CPS by enhancing their critical properties. We propose SafePilot, a novel hierarchical neuro-symbolic framework that provides end-to-end assurance for LLM-enabled CPS according to attribute-based and temporal specifications. Given a task and its specification, SafePilot first invokes a hierarchical planner with a discriminator that assesses task complexity. If the task is deemed manageable, it is passed directly to an LLM-based task planner with built-in verification. Otherwise, the hierarchical planner applies a divide-and-conquer strategy, decomposing the task into sub-tasks, each of which is individually planned and later merged into a final solution. The LLM-based task planner translates natural language constraints into formal specifications and verifies the LLM's output against them. If violations are detected, it identifies the flaw, adjusts the prompt accordingly, and re-invokes the LLM. This iterative process continues until a valid plan is produced or a predefined limit is reached. Our framework supports LLM-enabled CPS with both attribute-based and temporal constraints. Its effectiveness and adaptability are demonstrated through two illustrative case studies.
Weizhe Xu, Mengyu Liu, Fanxin Kong
University of Notre Dame, Notre Dame, IN, USA · Washington State University, Richland, WA, USA
Falsification searches for counterexamples to formal specifications in cyber-physical systems (CPS). With specifications written in Signal Temporal Logic (STL), falsification can be formulated as a robustness optimization problem, traditionally tackled with black-box search algorithms. In parallel, large language models (LLMs) have recently emerged as surprisingly effective optimizers when coupled with iterative prompting. In this work, we connect these ideas and introduce LLM-Falsifier, an LLM-based approach that falsifies specifications by minimizing the STL robustness degree. Beyond generic prompt-based optimization, our key idea is to expose the LLM to semantic information that is natural for language models but absent from standard numerical optimizers, including natural-language input and output names, output trajectories, and critical-time witnesses for the minimum robustness value. These additions enable smarter and more sample-efficient robustness search. On the ARCH-COMP falsification benchmarks, LLM-Falsifier is shown to outperform existing falsification tools based on a range of optimization paradigms, from surrogate-based and Bayesian optimization to search-based testing, on 14 of 21 specifications when measured by the average number of simulations required to find a counterexample.
Ali ArjomandBigdeli, Jiawei Zhou, Stanley Bak
Stony Brook University, Stony Brook, New York, USA
Autonomous cyber-physical systems (CPS) sit at the intersection of Model-Based Systems Engineering (MBSE) and data-driven Machine Learning and Artificial Intelligence (ML/AI), yet no integrated Systems Engineering (SE) methodology natively spans both. We address this gap with IDDMBSE, an Integrated Data-Driven and Model-Based Systems Engineering methodology that extends the rigorous MBSE V-process with a data-driven loop at every step, anchored in SysML, the autonomy stack, and a hybrid model-based plus data-driven trade-off architecture. We instantiate IDDMBSE as an interoperable, open-source tool chain: PERFECT, which maps SysML system architectures to executable ROS autonomy stacks for scalable performance evaluation; TRADES-X, which decomposes design-space exploration into a model-based optimization stage followed by a data-driven evaluation stage; and VERITAS, which combines formal, data-driven, and runtime verification into a single assurance workflow. We demonstrate IDDMBSE on a Trusted Autonomous Ground Robot across its development lifecycle, spanning sensor-suite selection, risk-sensitive path planning, behavior-tree task verification, conformal-prediction-based robust perception, and assured multi-robot coordination, all exercised in a contested-terrain Isaac Sim test range that we release with the tool chain. We close by sketching how IDDMBSE is being re-formulated on SysML v2 / KerML foundations to enable language-native composability and tighter ML/AI integration.
John S. Baras, Sai Sandeep Damera, Ryan Matheu +2
Institute for Systems Research, University of Maryland, College Park, MD, USA