Related papers: The Foundation Cracks: A Comprehensive Study on Bu…

Large language model-specific inference engines (in short as \emph{LLM inference engines}) have become a fundamental component of modern AI infrastructure, enabling the deployment of LLM-powered applications (LLM apps) across cloud and…

Numerous approaches employing various strategies have been developed to test the graphical user interfaces (GUIs) of mobile apps. However, traditional GUI testing techniques, such as random and model-based testing, primarily focus on…

With the rapid development of large language models (LLMs), distributed training and inference frameworks like DeepSpeed have become essential for scaling model training and inference across multiple GPUs or nodes. However, the increasing…

API misuse in code generated by large language models (LLMs) presents a serious and growing challenge in software development, as although LLMs demonstrate impressive code generation capabilities, their interactions with complex library…

Deep learning (DL) libraries, widely used in AI applications, often contain vulnerabilities like buffer overflows and use-after-free errors. Traditional fuzzing struggles with the complexity and API diversity of DL libraries such as…

Large language models (LLMs) are being rapidly integrated into decision-support tools, automation workflows, and AI-enabled software systems. However, their behavior in production environments remains poorly understood, and their failure…

Deep learning has gained substantial popularity in recent years. Developers mainly rely on libraries and tools to add deep learning capabilities to their software. What kinds of bugs are frequently found in such software? What are the root…

With advances in large language models (LLMs), new opportunities have emerged to develop tools that support the digital hardware design process. In this work, we explore how LLMs can assist with explaining the root cause of design issues…

Large Language Models (LLMs) have demonstrated exceptional coding capability. However, as another critical component of programming proficiency, the debugging capability of LLMs remains relatively unexplored. Previous evaluations of LLMs'…

Large Language Models (LLMs) transform artificial intelligence, driving advancements in natural language understanding, text generation, and autonomous systems. The increasing complexity of their development and deployment introduces…

LLM agents have been widely adopted in real-world applications, relying on agent frameworks for workflow execution and multi-agent coordination. As these systems scale, understanding bugs in the underlying agent frameworks becomes critical.…

Many automated test generation techniques have been developed to aid developers with writing tests. To facilitate full automation, most existing techniques aim to either increase coverage, or generate exploratory inputs. However, existing…

Large language models (LLMs), pre-trained or fine-tuned on large code corpora, have shown effectiveness in generating code completions. However, in LLM-based code completion, LLMs may struggle to use correct and up-to-date Application…

Bug reproduction is a critical developer activity that is also challenging to automate, as bug reports are often in natural language and thus can be difficult to transform to test cases consistently. As a result, existing techniques mostly…

Fault Localization (FL) aims to automatically localize buggy lines of code, a key first step in many manual and automatic debugging tasks. Previous FL techniques assume the provision of input tests, and often require extensive program…

Large language models (LLMs) provide effective solutions in various application scenarios, with the support of retrieval-augmented generation (RAG). However, developers face challenges in integrating LLM and RAG into software systems, due…

Large language models (LLMs) have driven significant progress across a wide range of real-world applications. Realizing such models requires substantial system-level support. Deep learning (DL) frameworks provide this foundation by enabling…

The automated program repair field has attracted substantial interest over the years, but despite significant research efforts, creating a system that works well for complex semantic bugs such as security vulnerabilities has proven…

Large Language Models (LLMs) have recently been used to generate mutants in both research work and in industrial practice. However, there has been no comprehensive empirical study of their performance for this increasingly important…

Deep learning (DL) libraries are widely used in critical applications, where even subtle silent bugs can lead to serious consequences. While existing DL fuzzing techniques have made progress in detecting crashes, they inherently struggle to…