Searcharxiv⌕ Search

arXiv subjects

Aitor Arrieta

Publications and source records attributed to Aitor Arrieta.

At least 19 recordsLinked to original sources

VoxelSBFL: Voxel-Level Spectrum-Based Failure Prediction for Vision-Language-Action Models

Vision-Language-Action (VLA) models integrate visual perception, language understanding, and action generation to control robots. Testing these systems produces trajectories and task outcomes, but existing approaches provide limited guidance on using these recorded trajectories to assess subsequent executions or inform policy repair. We conjecture that, for a given policy and task, traversing certain workspace regions is associated with a higher likelihood of failure. To investigate this conjecture, we propose VoxelSBFL, a black-box adaptation of Spectrum-Based Fault Localization (SBFL) in which workspace voxels replace program elements as units of analysis. Recorded tool-center-point (TCP) trajectories provide binary voxel coverage, which is combined with execution outcomes to construct suspiciousness maps using established SBFL formulas. These maps identify failure-associated regions and score unseen trajectories without requiring internal model access. We evaluate 34 spectrum-based techniques across four VLA models using 96,000 Pick-Up trajectories in simulation and compare the leading techniques against eight action- and trajectory-based metrics. VoxelSBFL obtains an overall macro ROC-AUC of 0.704, significantly outperforming state-of-the art baselines. Sensitivity analyses show that performance varies with spatial granularity and training-set size. These findings support spatial spectra for VLA execution assessment and motivate future research on runtime monitoring, self-healing and targeted policy improvement.

cs.RO↗

MANGO: Automated Multi-Agent Test Oracle Generation for Vision-Language-Action Models

Vision-Language-Action (VLA) models are emerging robotic control systems that integrate perception, language understanding, and action generation in a unified architecture. Existing testing approaches for VLA-enabled robots rely on manually constructed symbolic test oracles that determine task success from final environment states. These oracles are costly to construct, require domain expertise, and are often tightly coupled to specific tasks and environments, limiting scalability and reuse. Furthermore, they provide only end-state assessments of task outcomes, offering limited insight into intermediate behavior and fault localization. To address these limitations, we introduce MANGO, a multi-agent framework that automatically generates fine-grained oracles from natural-language descriptions of robotic tasks. MANGO first generates a reusable library of atomic tasks, then generates simulator-grounded oracle definitions for each atomic task, and finally produces executable fine-grained oracles by decomposing complex instructions into ordered sequences of atomic actions and corresponding oracles. The framework uses collaborative Generator, Assessor, and Judge agents that iteratively refine generated artifacts through structured feedback. We evaluate MANGO on the LIBERO_10 and RoboCasa Humanoid Tabletop benchmarks. Results show that MANGO generates executable, fine-grained oracles that detect a similar number of failures as symbolic oracles while accurately localizing them and providing richer diagnostic information. Through ablation studies, we further analyzed component contributions and the effect of initial task set, while preserving oracle quality. Overall, the results show the feasibility and effectiveness of test oracle generation for VLA-enabled robots testing.

cs.SE↗

Search-Based Metamorphic Testing of Vision-Language Models in Autonomous Underwater Robotic Software

Our industry partner focuses on quality assurance for industrial systems across multiple domains, including maritime systems, such as overwater vessels and autonomous underwater robots (AURs). Despite the strong performance of vision-language models (VLMs) in scene understanding, image captioning, and object recognition, their use in AUR software operating in underwater environments is underexplored. Therefore, in this context, it is important to evaluate the quality of VLMs for integration into AUR software and, so, automated software testing tools are needed to assess their suitability and improve their dependability. To this end, we propose a search-based metamorphic testing approach (MetaVLM) that identifies a minimal set of transformations on underwater images to induce incorrect model predictions, thereby revealing VLM failures. We employ NSGA-II as a multi-objective search algorithm and evaluate it over open-source VLMs, BLIP and CLIP, against a random search baseline. Results demonstrate the strengths and limitations of each VLM in the context of AUR software systems. Based on the results, we derive lessons for software engineering practitioners and researchers working on quality assurance of VLM-based software systems.

cs.SE↗

Evaluating Uncertainty and Quality of Vision-Language-Action-enabled Robots

Vision-Language-Action (VLA)-enabled robots integrate visual perception, natural language understanding, and action planning to interpret their environment, comprehend instructions, and perform embodied tasks autonomously. Such robots are typically evaluated through task success rates, i.e., whether a robot performs its intended task, which are commonly used as test oracles for evaluating such robots. Such an evaluation fails to capture the quality of task execution and the robot's confidence in its decisions. In this paper, we adapt eight uncertainty metrics and five quality metrics specifically designed for VLA-enabled robotic manipulation tasks. We assess their effectiveness through a large-scale empirical study involving 908 successful task executions from three state-of-the-art VLA models across four representative robotic manipulation tasks and two robot embodiments. Human domain experts manually labeled task quality, enabling us to analyze the correlation between our proposed metrics and expert judgments, serving as a human oracle for testing such robots. The results reveal that several metrics show moderate to strong correlation with human assessments, highlighting their utility for evaluating task quality and model confidence. Furthermore, we found that some metrics can discriminate between high-, medium-, and low-quality executions from unsuccessful tasks, which is useful when test oracles are absent. Our findings challenge the adequacy of current evaluation practices that rely solely on binary success rates and pave the way for improved real-time monitoring and adaptive enhancement of VLA-enabled robots.

cs.SE↗

Hype Meets Reality: Large Language Models as Mutators in Search-based Automated Program Repair of Simulink-Stateflow Models

Search-based Automated Program Repair (APR) techniques rely on carefully designed mutation operators to explore the space of candidate fixes. Recent advances in Large Language Models (LLMs) suggest that generative models could replace such operators by dynamically proposing repairs. In this paper, we investigate this hypothesis in the context of Cyber-Physical Systems (CPSs) modeled in Simulink/Stateflow. We extend the state-of-the-art FlowRepair approach by replacing a subset of its mutation operators with LLM-generated mutations, enabling more flexible and expressive patch generation. We evaluate the approach on a benchmark of 19 real-world faulty Stateflow models across four CPS domains, using the same experimental setup as FlowRepair for controlled comparison under the same wall-clock budget. Contrary to expectations, in this controlled evaluation, the LLM-based mutation substantially degrades repair performance under the FlowRepair experimental setup. Across the tested LLM variants, the LLM-based repair produced plausible patches for 4-6 models and valid patches for 4 models, compared to 18 and 16, respectively, with the original approach. Our analysis reveals that, in this integration, LLMs struggle with precise symbolic edits, lack behavioral feedback, and generate a noisy search space that hinders effective exploration. Rather than showing a general limitation of LLMs for APR, these findings highlight fundamental limitations of naively integrating LLMs into search-based APR and motivate hybrid approaches that combine structured mutation with generative guidance.

cs.SE↗

Uncertainty in Cyber-Physical Systems: A Literature Survey

Cyber-Physical Systems (CPSs) operate in dynamic, dependable environments where sensing, communication, decision-making, control, and assurance are affected by uncertainty. This paper characterizes CPS uncertainty through a literature survey comprising 186 primary studies. We (i) characterize uncertainty types, (ii) identify uncertainty sources, (iii) relate uncertainty to life-cycle phases in which they occur, and (iv) overview the possible uncertain mitigation strategies. The findings show that uncertainty is most often conceptualized as an assurance issue. Safety and specification uncertainty is the most prevalent category, followed by environmental and model/epistemic uncertainty. Domain mapping reveals broad cross-domain engagement, while safety-critical sectors such as autonomous systems, energy systems, and robotics CPSs display domain-specific uncertainty patterns. The life-cycle analysis indicates that uncertainty is not limited to the development or testing phases but also arises during runtime operation, underscoring the need for continuous assurance approaches. Mitigation strategies primarily include runtime monitoring, robust and adaptive control, and probabilistic reasoning. In summary, this survey contributes to a thorough characterization of CPS uncertainty and provides a discussion of articles on this topic.

cs.SE↗

Delta Debugging for Cyber-Physical Systems with Flaky Test Executions

Simulation-based testing is widely used to validate Cyber-Physical Systems (CPSs), yet modern CPS simulators frequently exhibit non-deterministic (flaky) behavior, making failures difficult to reproduce and debug. Although delta debugging has proven effective for deterministic systems, its underlying assumptions do not hold in stochastic environments. This paper presents three delta debugging algorithms that combine statistical failure analysis, repeated executions, and environment-aware reduction to isolate minimal failure-inducing test inputs for stochastic CPSs. We evaluate the proposed techniques on two complementary case study systems: an industrial elevator dispatching system employing stochastic optimization and an autonomous mobile robot exhibiting simulator-induced non-determinism. The results show that the proposed approaches substantially reduce debugging time while preserving the original failure behavior. More importantly, we observe that minimizing failure-inducing test inputs frequently increases failure reproducibility compared with the original executions. By eliminating execution segments that introduce incidental stochastic effects, the reduced test inputs isolate the causal conditions of the failure and consistently reproduce it with higher probability. These findings suggest that delta debugging not only simplifies failure analysis but also mitigates execution flakiness, providing a practical foundation for debugging CPSs.

cs.SE↗

RAG-TESTER: Automated End-to-End Testing of Retrieval-Augmented Large Language Models

Retrieval-Augmented Generation (RAG) enables Large Language Models (LLMs) to use external and domain-specific knowledge, but its reliability depends on the interaction between the generative model, embedding model, retrieval mechanism, and prompt construction strategy. We present RagTester, an automated end-to-end testing approach for RAG systems. RagTester generates retrieval documents, test inputs, and expected outputs; executes the tests; and evaluates the resulting answers using an LLM as a judge. Its test-generation strategy targets complex passages, unsupported queries, and document-coverage criteria. We evaluate RagTester using eight LLMs and six embedding models, yielding 24 compatible configurations, and compare it with a baseline test-input generator. Across 72,000 test executions, RagTester detected 21,633 failures, 6.6% more than the baseline, and outperformed it in 20 of the 24 configurations. The detected failures include inaccurate retrieval, unsupported answers, incomplete use of retrieved context, and difficulties interpreting complex passages. These results show that coverage-oriented test generation can effectively expose failures caused by the interaction between retrieval and generation components and support the assessment of RAG configurations before deployment.

cs.AI↗

Generalizable Robustness Testing of DNN-Based Robotic Navigation Systems via XAI-Guided Search

**Context:** Deep Neural Networks (DNNs) increasingly control Cyber-Physical Systems (CPSs), yet small input perturbations can cause unsafe system-level behavior. Existing approaches often optimize perturbations for individual images and evaluate them only in simulation, limiting their generalizability and practical validity. **Objectives:** This work aims to generate robustness tests that remain effective across operational observations and to evaluate whether the resulting failures transfer from simulation to a physical robot. **Methods:** We propose an explainability-guided multi-objective evolutionary approach that generates sparse perturbations over representative images selected through visual and behavioral clustering. Aggregated Integrated Gradients guide mutations toward influential image regions. We evaluate the approach on a DNN-controlled LeoRover in Gazebo, conduct an ablation study, and validate a stratified subset of perturbations on the physical robot. **Results:** The approach achieved a median success rate of 70.0%, compared with 53.85% for unguided search, and increased median hypervolume from 0.65 to 0.73. Multi-image optimization improved the success rate from 50.0% to 57.5%, while XAI guidance further increased it to 70.0%. In the sim-to-real evaluation, simulation achieved 0.95 precision and 0.67 recall, and simulated and physical failure times showed a significant positive correlation of 0.617. **Conclusion:** Combining multi-image optimization with explainability-guided search improves robustness testing for DNN-controlled robotic systems. Simulation effectively identifies and prioritizes transferable failures, but physical validation remains necessary because some real-world failures are not reproduced in simulation.

cs.RO↗

Foundation Models for Software Engineering of Cyber-Physical Systems: the Road Ahead

Foundation Models (FMs), particularly Large Language Models (LLMs), are increasingly used to support various software engineering activities (e.g., coding and testing). Their adoption in software engineering of Cyber-Physical Systems (CPSs) is also growing. However, research in this area remains limited. Most existing studies have primarily focused on LLMs, only one type of FM, leaving ample opportunities to explore other FMs, such as vision-language models. We argue that, in addition to LLMs, other FMs utilizing different data modalities (e.g., images, audio) and multimodal models (which integrate multiple modalities) hold great potential for supporting CPS software engineering, given that these systems process diverse data types. To address this, in this first systematic effort, we present a forward-looking research roadmap for integrating FMs into commonly known phases of CPS software engineering, thereby making it accessible to most software engineers. We derive the roadmap from the literature, emerging trends in FMs, and gaps identified from the literature. The roadmap highlights key challenges and actionable research opportunities for the software engineering community to guide future research. Moreover, we discuss the common challenges associated with applying FMs across six dimensions (e.g., technical, economic and resource, and human aspects). This roadmap aims to provide a visionary guide for researchers and practitioners, outlining directions for future work and performing future empirical studies.

cs.SE↗

FATE-VLA:Failue-aware test generation for vision-language-action models

Vision-Language-Action (VLA) models are increasingly used as generalist robot policies, yet their evaluation still relies largely on static benchmarks that randomly sample task scenes. In high-dimensional embodied spaces, failures are sparse and clustered, so static benchmarking can underestimate robustness risks. We reframe VLA evaluation as an active failure-discovery problem and propose a failure-aware test-generation approach that combines diversity-driven exploration with surrogate models learned from observed executions. The method steers testing toward high-risk yet diverse scene regions. Across four state-of-the-art VLA models, it uncovers substantially more failures (up to +29.7 % over selected baselines) while revealing more diverse failure modes. This mean that, for instance, in the case of GR00T-N1.6, success rate dropped from 64.4% to 34.7%. More broadly, our findings call for a shift in VLA evaluation: from passive measurement on fixed task suites to adaptive, failure-seeking test generation that exposes the structure of model weaknesses before deployment.

cs.RO↗

VISOR: A Vision-Language Model-based Test Oracle for Testing Robots

Testing robots requires assessing whether they perform their intended tasks correctly, dependably, and with high quality, a challenge known as the test oracle problem in software testing. Traditionally, this assessment relies on task-specific symbolic oracles for task correctness and on human manual evaluation of robot behavior, which is time-consuming, subjective, and error-prone. To address this, we propose VISOR, a Vision-Language Model (VLM)-based approach for automated test oracle assessment that eliminates the need of expensive human evaluations. VISOR performs automated evaluation of task correctness and quality, addressing the limitations of existing symbolic test oracles, which are task-specific and provide pass/fail judgments without explicitly quantifying task quality. Given the inherent uncertainty in VLMs, VISOR also explicitly quantifies its own uncertainty during test assessments. We evaluated VISOR using two VLMs, i.e., GPT and Gemini, across four robotic tasks on over 1,000 videos. Results show that Gemini achieves higher recall while GPT achieves higher precision. However, both models show low correlation between uncertainty and correctness, which prevents using uncertainty as a correctness predictor.

cs.SE↗

Reinforcement Learning for Testing Interdependent Requirements in Autonomous Vehicles: An Empirical Study

Autonomous vehicles (AVs) make driving decisions without humans, making dependability assurance critical. Scenario-based testing is widely used to evaluate AVs under diverse conditions, with reinforcement learning (RL) generating test scenarios that identify violations of functional and safety requirements. Many requirements are interdependent and involve trade-offs, making it unclear whether single-objective RL (SORL), which combines objectives into a single reward, can reliably reveal violations or whether multi-objective RL (MORL), which explicitly considers multiple objectives, is necessary. We present an empirical evaluation comparing SORL and MORL for generating critical scenarios that simultaneously test interdependent requirements using an end-to-end AV controller and high-fidelity simulator. Results suggest that MORL and SORL differ mainly in how violations occur, while showing comparable effectiveness in many cases. MORL tends to generate more requirement-violation scenarios, whereas SORL produces higher-severity violations. Their relative performance also depends on specific objective combinations and, to a lesser extent, road conditions. Regarding diversity, MORL consistently covers a broader range of scenarios. Thus, MORL is preferable when scenario diversity and coverage are prioritized, whereas SORL may better expose severe violations. Our empirical evaluation addresses a gap by systematically comparing SORL and MORL, highlighting the importance of requirement dependencies in RL-based AV testing.

cs.SE↗

Assessing Vision-Language Models for Perception in Autonomous Underwater Robotic Software

Autonomous Underwater Robots (AURs) operate in challenging underwater environments, including low visibility and harsh water conditions. Such conditions present challenges for software engineers developing perception modules for the AUR software. To successfully carry out these tasks, deep learning has been incorporated into the AUR software to support its operations. However, the unique challenges of underwater environments pose difficulties for deep learning models, which often rely on labeled data that is scarce and noisy. This may undermine the trustworthiness of AUR software that relies on perception modules. Vision-Language Models (VLMs) offer promising solutions for AUR software as they generalize to unseen objects and remain robust in noisy conditions by inferring information from contextual cues. Despite this potential, their performance and uncertainty in underwater environments remain understudied from a software engineering perspective. Motivated by the needs of an industrial partner in assurance and risk management for maritime systems to assess the potential use of VLMs in this context, we present an empirical evaluation of VLM-based perception modules within the AUR software. We assess their ability to detect underwater trash by computing performance, uncertainty, and their relationship, to enable software engineers to select appropriate VLMs for their AUR software.

cs.SE↗

Metamorphic Testing of Vision-Language Action-Enabled Robots

Vision-Language-Action (VLA) models are multimodal robotic task controllers that, given an instruction and visual inputs, produce a sequence of low-level control actions (or motor commands) enabling a robot to execute the requested task in the physical environment. These systems face the test oracle problem from multiple perspectives. On the one hand, a test oracle must be defined for each instruction prompt, which is a complex and non-generalizable approach. On the other hand, current state-of-the-art oracles typically capture symbolic representations of the world (e.g., robot and object states), enabling the correctness evaluation of a task, but fail to assess other critical aspects, such as the quality with which VLA-enabled robots perform a task. In this paper, we explore whether Metamorphic Testing (MT) can alleviate the test oracle problem in this context. To do so, we propose two metamorphic relation patterns and five metamorphic relations to assess whether changes to the test inputs impact the original trajectory of the VLA-enabled robots. An empirical study involving five VLA models, two simulated robots, and four robotic tasks shows that MT can effectively alleviate the test oracle problem by automatically detecting diverse types of failures, including, but not limited to, uncompleted tasks. More importantly, the proposed MRs are generalizable, making the proposed approach applicable across different VLA models, robots, and tasks, even in the absence of test oracles.

cs.RO↗

Vision Language Model-based Testing of Industrial Autonomous Mobile Robots

PAL Robotics, in Spain, builds a variety of Autonomous Mobile Robots (AMRs), which are deployed in diverse environments (e.g., warehouses, retail spaces, and offices), where they work alongside humans. Given that human behavior can be unpredictable and that AMRs may not have been trained to handle all possible unknown and uncertain behaviors, it is important to test AMRs under a wide range of human interactions to ensure their safe behavior. Moreover, testing in real environments with actual AMRs and humans is often costly, impractical, and potentially hazardous (e.g., it could result in human injury). To this end, we propose a Vision Language Model (VLM)-based testing approach (RVSG) for industrial AMRs developed together with PAL Robotics. Based on the functional and safety requirements, RVSG uses the VLM to generate diverse human behaviors that violate these requirements. We evaluated RVSG with several requirements and navigation routes in a simulator using the latest AMR from PAL Robotics. Our results show that, compared with the baseline, RVSG can effectively generate requirement-violating scenarios. Moreover, RVSG-generated scenarios increase variability in robot behavior, thereby helping reveal their uncertain behaviors.

cs.SE↗

Exploring the Potential of Large Language Models in Simulink-Stateflow Mutant Generation

Mutation analysis is a powerful technique for assessing test-suite adequacy, yet conventional approaches suffer from generating redundant, equivalent, or non-executable mutants. These challenges are particularly amplified in Simulink-Stateflow models due to the hierarchical structure these models have, which integrate continuous dynamics with discrete-event behaviors and are widely deployed in safety-critical Cyber-Physical Systems (CPSs). While prior work has explored machine learning and manually engineered mutation operators, these approaches remain constrained by limited training data and scalability issues. Motivated by recent advances in Large Language Models (LLMs), we investigate their potential to generate high-quality, domain-specific mutants for Simulink-Stateflow models. We develop an automated pipeline that converts Simulink-Stateflow models to structured JSON representations and systematically evaluates different mutation and prompting strategies across eight state-of-the-art LLMs. Through a comprehensive empirical study involving 38,400 LLM-generated mutants across four Simulink-Stateflow models, we demonstrate that LLMs generate mutants up to 13x faster than a manually engineered mutation-based baseline while producing significantly fewer equivalent and duplicate mutants and consistently achieving superior mutant quality. Moreover, our analysis reveals that few-shot prompting combined with low-to-medium temperature values yields optimal results. We provide an open-source prototype tool and release our complete dataset to facilitate reproducibility and advance future research in this domain.

cs.SE↗

Meta-Fair: AI-Assisted Fairness Testing of Large Language Models

Fairness--the absence of unjustified bias--is a core principle in the development of Artificial Intelligence (AI) systems, yet it remains difficult to assess and enforce. Current approaches to fairness testing in large language models (LLMs) often rely on manual evaluation, fixed templates, deterministic heuristics, and curated datasets, making them resource-intensive and difficult to scale. This work aims to lay the groundwork for a novel, automated method for testing fairness in LLMs, reducing the dependence on domain-specific resources and broadening the applicability of current approaches. Our approach, Meta-Fair, is based on two key ideas. First, we adopt metamorphic testing to uncover bias by examining how model outputs vary in response to controlled modifications of input prompts, defined by metamorphic relations (MRs). Second, we propose exploiting the potential of LLMs for both test case generation and output evaluation, leveraging their capability to generate diverse inputs and classify outputs effectively. The proposal is complemented by three open-source tools supporting LLM-driven generation, execution, and evaluation of test cases. We report the findings of several experiments involving 12 pre-trained LLMs, 14 MRs, 5 bias dimensions, and 7.9K automatically generated test cases. The results show that Meta-Fair is effective in uncovering bias in LLMs, achieving an average precision of 92% and revealing biased behaviour in 29% of executions. Additionally, LLMs prove to be reliable and consistent evaluators, with the best-performing models achieving F1-scores of up to 0.79. Although non-determinism affects consistency, these effects can be mitigated through careful MR design. While challenges remain to ensure broader applicability, the results indicate a promising path towards an unprecedented level of automation in LLM testing.

cs.SE↗