Deep Learning (DL) is a class of machine learning algorithms that are used in a wide variety of applications. Like any software system, DL programs can have bugs. To support bug localization in DL programs, several tools have been proposed in the past. As most of the bugs that occur due to improper model structure known as structural bugs lead to inadequate performance during training, it is challenging for developers to identify the root cause and address these bugs. To support bug detection and localization in DL programs, in this article, we propose Theia, which detects and localizes structural bugs in DL programs. Unlike the previous works, Theia considers the training dataset characteristics to automatically detect bugs in DL programs developed using two DL libraries, Keras and PyTorch . Since training the DL models is a time-consuming process, Theia detects these bugs at the beginning of the training process and alerts the developer with informative messages containing the bug’s location and actionable fixes which will help them to improve the structure of the model. We evaluated Theia on a benchmark of 40 real-world buggy DL programs obtained from Stack Overflow . Our results show that Theia successfully localizes 57/75 structural bugs in 40 buggy programs, whereas NeuraLint, a state-of-the-art approach capable of localizing structural bugs before training localizes 17/75 bugs.

Deep learning models, particularly Convolutional Neural Networks (CNNs), play a pivotal role in intelligent software. However, like any software application, CNN-based applications are susceptible to bugs. Bug-fix patterns in CNN differ from traditional techniques, primarily due to their inherent black box nature. Moreover, current methods, although tailored for generic DNN structures, are time consuming, require specialized expertise, and are not directly applicable to the unique structure and requirements of CNNs. To address these issues, we propose DeepCNN, an innovative automated tool to identify the root causes of CNN faults and autonomously fix prevalent training faults that impact the performance and efficiency of CNN programs. DeepCNN, a data-driven tool, employs a transformer encoder model to abstract token-level CNN code, enabling it to effectively detect and fix bugs in real-world CNN models. Beyond mere identification, DeepCNN offers automated solutions for repairing CNN hyperparameter misconfigurations using an optimization solver. Additionally, by analyzing data dependencies and employing a search algorithm, it determines the most optimal hyperparameter values for the problematic models, ultimately generating patch fixes. Through rigorous evaluation on 36 diverse buggy models, DeepCNN outperformed existing methods in fault localization and repair, showing a robustness in identifying potential problems with a 90% detection rate. Among these problematic models, it manages to repair 90% of them — resulting in a 30% average accuracy boost.

In software, a vulnerability is a defect in a program that attackers might utilize to acquire unauthorized access, alter system functions, and acquire information. These vulnerabilities arise from programming faults, design flaws, incorrect setups, and a lack of security protective measures. To mitigate these vulnerabilities, regular software upgrades, code reviews, safe development techniques, and the use of security tools to find and fix problems have been important. Several ways have been delivered in recent studies to address difficulties related to software vulnerabilities. However, previous approaches have significant limitations, notably in feature embedding and precisely recognizing specific vulnerabilities. To overcome these drawbacks, we present CodeGraphNet, an experimental method that combines GraphCodeBERT and Graph Convolutional Network (GCN) approaches, where, CodeGraphNet reveals data in a high-dimensional vector space, with comparable or related properties grouped closer together. This method captures intricate relationships between features, providing for more exact identification and separation of vulnerabilities. Using this feature embedding approach, we employed four machine learning models, applying both independent testing and 10-fold cross-validation. The DeepTree model, which is a hybrid of a Decision Tree and a Neural Network, outperforms state-of-the-art approaches. In additional validation, we evaluated our model using feature embeddings from LSA, GloVe, FastText, CodeBERT and GraphCodeBERT, and found that the CodeGraphNet method presented improved vulnerability identification with 98% of accuracy. Our model was tested on a real-time dataset to determine its capacity to handle real-world data and to focus on defect localization, which might influence future studies.

Effectively testing Artificial Intelligence (AI) agents remains a fundamental challenge due to their stochastic reasoning, vast and diverse input space, reliance on external tools, and operation in dynamic execution environments; factors that demand new testing methodologies explicitly tailored to the complex and interactive nature of agent-based systems. This work presents a novel methodology for testing AI agents, with a particular focus on assessing their behavioral robustness under varied operational conditions. Our approach relies on following key technical innovations: (1) a coverage-guided test input generation strategy based on agent- specific coverage objectives, (2) a capture-and-simulate mechanism that systematically emulates abnormal tool behaviors to mimic real-world execution failures, and (3) a deterministic behavioral failure detection approach that enables consistent identification of failures across different test inputs. We developed AgentInspect, a framework that automatically detects six types of behavioral failures in LangChain-based AI agents by analyzing their execution trajectories across three evaluation settings: a baseline setting using real tool responses, a simulated setting incorporating synthetic tool responses, and a hybrid setting that combines the real and simulated tool responses. To evaluate our approach, we curated a benchmark of 35 AI agents obtained from GitHub. Our results show that AgentInspect consistently identifies different behavioral failures with high precision and recall across all three execution settings. In particular, the simulated and hybrid settings expose failure modes that do not emerge during baseline execution with real tool responses, thereby enabling a more comprehensive assessment of agent robustness. Our findings highlight AgentInspect’s effectiveness in revealing critical failures and its practical utility for systematic robustness evaluation of AI agents.