Related papers: DebugHarness: Emulating Human Dynamic Debugging fo…
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…
Unlike code completion, debugging requires localizing faults and applying targeted edits. We observe that frontier LLMs often regenerate correct but over-edited solutions during debugging. To evaluate how far LLMs are from precise…
Background: Automated Vulnerability Repair (AVR) is a fast-growing branch of program repair. Recent studies show that large language models (LLMs) outperform traditional techniques, extending their success beyond code generation and fault…
Large Language Models (LLMs) have transformed software development and AI applications. While LLMs are designed for text processing, LLM agents extend this capability by enabling autonomous actions, tool use, and multi-step task completion.…
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…
Bug fixing and code generation have been core research topics in software development for many years. The recent explosive growth in Large Language Models has completely transformed these spaces, putting in reach incredibly powerful tools…
Fault localization has been determined as a major resource factor in the software development life cycle. Academic fault localization techniques are mostly unknown and unused in professional environments. Although manual debugging…
Fully autonomous teams of LLM-powered AI agents are emerging that collaborate to perform complex tasks for users. What challenges do developers face when trying to build and debug these AI agent teams? In formative interviews with five AI…
Context: Traditional software security analysis methods struggle to keep pace with the scale and complexity of modern codebases, requiring intelligent automation to detect, assess, and remediate vulnerabilities more efficiently and…
Large language models (LLMs) have shown impressive effectiveness in various software engineering tasks, including automated program repair (APR). In this study, we take a deep dive into automated bug fixing utilizing LLMs. In contrast to…
Aim: With the advent of LLMs, sophisticated agentic program repair has become viable at large organizations with large codebases. In this work, we develop an Engineering Agent that fixes the source code based on test failures at scale…
Fuzzing is a widely used software security testing technique that is designed to identify vulnerabilities in systems by providing invalid or unexpected input. Continuous fuzzing systems like OSS-FUZZ have been successful in finding security…
Training large language models (LLMs) on Python execution traces grounds them in code execution and enables the line-by-line execution prediction of whole Python programs, effectively turning them into neural interpreters (FAIR CodeGen Team…
LLMs have garnered considerable attention for their potential to streamline Automated Program Repair (APR). LLM-based approaches can either insert the correct code or directly generate patches when provided with buggy methods. However, most…
RTL program repair remains a critical bottleneck in hardware design and verification. Traditional automatic program repair (APR) methods rely on predefined templates and synthesis, limiting their bug coverage. Large language models (LLMs)…
LLMs are transforming software development, yet current code generation and code repair benchmarks mainly assess syntactic and functional correctness in simple, single-error cases. LLMs' capabilities to autonomously find and fix runtime…
Over the years of challenges on detecting the crash consistency of non-volatile persistent memory (PM) bugs and developing new tools to identify those bugs are quite stretching due to its inconsistent behavior on the file or storage…
The increasing prevalence of software bugs has made automated program repair (APR) a key research focus. Large language models (LLMs) offer new opportunities for APR, but existing studies mostly rely on smaller, earlier-generation models…
Large Language Models (LLMs) have demonstrated remarkable performance in code completion. However, the training data used to develop these models often contain a significant amount of buggy code. Yet, it remains unclear to what extent these…
Large Language Models (LLMs) such as ChatGPT-4, Claude 3, and LLaMA 4 are increasingly embedded in software/application development, supporting tasks from code generation to debugging. Yet, their real-world effectiveness in detecting…