Related papers: PAGENT: Learning to Patch Software Engineering Age…

The sudden emergence of large language models (LLMs) such as ChatGPT has had a disruptive impact throughout the computing education community. LLMs have been shown to excel at producing correct code to CS1 and CS2 problems, and can even act…

AI coding agents demonstrate strong performance on general-purpose software benchmarks. However, their ability to handle 5G network engineering tasks remains unexplored. We propose SWE-Bench~5G, the first benchmark designed to investigate…

Function-level code generation leverages foundation Large Language Models (LLMs) to automatically produce source code with expected functionality. It has been widely investigated and applied in intelligent programming assistants, such as…

Large Language Models (LLMs) have enabled intelligent agents that autonomously interact with environments and invoke external tools. Recently, agent-based software repair has drawn wide attention, as repair agents can localize bugs,…

LLM-based agents are increasingly deployed for software maintenance tasks such as automated program repair (APR). APR agents automatically fetch GitHub issues and use backend LLMs to generate patches that fix the reported bugs. However,…

Recent LLM-based systems have made automated vulnerability repair increasingly practical, but two challenges remain. First, without strong signals about where a bug originates, repair agents drift toward shallow edits that silence the…

The advent of large language models (LLMs) such as ChatGPT, PaLM, and GPT-4 has catalyzed remarkable advances in natural language processing, demonstrating human-like language fluency and reasoning capacities. This position paper introduces…

Rigorous security-focused evaluation of large language model (LLM) agents is imperative for establishing trust in their safe deployment throughout the software development lifecycle. However, existing benchmarks largely rely on synthetic…

When a multi-module LLM agent fails, the module most responsible for the failure is not necessarily the best place to intervene. We demonstrate this Diagnostic Paradox empirically: causal analysis consistently identifies the routing module…

Large Language Model (LLM) code agents increasingly resolve repository-level issues by iteratively editing code, invoking tools, and validating candidate patches. In these workflows, agents often write tests on the fly, but the value of…

Bug localization remains a key bottleneck in downstream software maintenance tasks, including root cause analysis, triage, and automated program repair (APR), despite recent advances in large language model (LLM)-based repair systems.…

This paper presents a method to automatically fix implicit data loss warnings in large C++ projects using Large Language Models (LLMs). Our approach uses the Language Server Protocol (LSP) to gather context, Tree-sitter to extract relevant…

Programmable packet-processing devices such as programmable switches and network interface cards are becoming mainstream. These devices are configured in a domain-specific language such as P4, using a compiler to translate packet-processing…

As Large Language Models (LLMs) increasingly generate code in software development, ensuring the quality of LLM-generated code has become important. Traditional testing approaches using Example-based Testing (EBT) often miss edge cases --…

LLM-based coding agents are rapidly being deployed in software development, yet their safety implications remain poorly understood. These agents, while capable of accelerating software development, may exhibit unsafe behaviors during normal…

Large Language Models (LLMs) have achieved remarkable success in automated code translation. While prior work has focused on improving translation accuracy through advanced prompting and iterative repair, the reliability of the underlying…

LLM-based agents have demonstrated great potential in generating and managing code within complex codebases. In this paper, we introduce WebGen-Bench, a novel benchmark designed to measure an LLM-based agent's ability to create multi-file…

Large Language Models (LLMs) are increasingly deployed to resolve real-world GitHub issues. However, despite their potential, the specific failure modes of these models in complex repair tasks remain poorly understood. To characterize how…

Software vulnerabilities continue to be ubiquitous, even in the era of AI-powered code assistants, advanced static analysis tools, and the adoption of extensive testing frameworks. It has become apparent that we must not simply prevent…

As the capabilities of Large Language Models (LLMs) continue to advance, the field of patent processing has garnered increased attention within the natural language processing community. However, the majority of research has been…