~ similar to 2607.23355· 20 results
The paper introduces TRAILS~, a novel method that improves code correctness validation by grounding LLM reasoning in concrete (input, output) pairs derived from specifications, achieving state-of-the-…
Ningzhi Tang, Chaoran Chen, Gelei Xu, Yiyu Shi +4 more
This study analyzes over 20,000 real-world coding sessions to show that AI coding agents frequently fail users through subtle misalignment, requiring constant manual correction even when major system…
Jun Zhang, JianYing Qu, Hanwen Du, Zhongkai Sun +2 more
The paper introduces Code-QA-Bench, a novel framework that rigorously separates genuine code reasoning from mere documentation memorization in repository-level code understanding benchmarks.
Nils Loose, Joseph Bienhüls, Kristoffer Hempel, Felix Mächtle +1 more
The paper evaluates code language model-based detection of vulnerability-fixing commits (VFCs) using a unified benchmark and concludes that code changes alone are insufficient for accurate detection,…
Jie Zhu, Penghui Li, Zhongxuan Li, Chihao Shen +3 more
The paper presents Symbolon, a framework that learns and applies context-sensitively diverse code transformations to improve symbolic execution, increasing coverage and reducing costs.
Tian Dong, Yanjun Chen, Shoufeng Zhang, Huaien Zhang +5 more
This paper measures the prevalence of recurring vulnerability patterns (variants) across multiple AI infrastructure repositories and proposes INFRASCOPE, a framework to automatically detect these vari…
Chenxing Zhong, Daniel Feitosa, Paris Avgeriou, Huang Huang +2 more
This paper introduces Pairwise Modular Smell (PairSmell) for identifying flawed architectural decisions and trains machine learning models to predict two forms of PairSmell using 19 pair characteristi…
This paper provides the first large-scale characterisation of Domain-Driven Design (DDD) adoption and implementation on GitHub.
James C. Davis, Paschal C. Amusuo, Tanmay Singla, Berk Çakar +1 more
This paper presents a case study on using AI coding agents in software engineering and develops a process model for governing high-velocity agentic implementation.
The paper introduces FVSpec, a large-scale benchmark that translates thousands of real-world Python property-based tests into formal Lean 4 specifications to evaluate AI models for formal software ver…
Huihui Huang, Jieke Shi, Bo Wang, Zhou Yang +1 more
MemHint is a neuro-symbolic static analysis pipeline that significantly improves memory leak detection in C/C++ by combining LLM semantic understanding with Z3 symbolic reasoning, detecting more leaks…
Mingyu Chen, Yakun Zhang, Zihao Xie, Yixing Luo +4 more
The paper proposes TraceDev, a multi-agent framework for automated software development grounded in use cases, achieving higher success rates than baseline approaches in repository-level code generati…
The paper analyzes a large dataset of JavaScript packages to demonstrate that a small number of vulnerable dependencies can propagate vulnerabilities across a disproportionately large number of packag…
Weixing Zhang, Bowen Jiang, Yuhong Fu, Haowei Cheng +2 more
This paper presents an empirical investigation on the distribution, evolution, and maintenance implications of Domain-Driven Design (DDD) building blocks in open-source GitHub repositories.
The paper introduces an execution-grounded, cross-language framework that significantly improves the reliability of LLM-driven code vulnerability analysis by ensuring that all proposed fixes are confi…
The paper introduces codebadger, a Model Context Protocol (MCP) server that integrates Joern's Code Property Graph (CPG) with LLMs, enabling large language models to perform large-scale, semantic prog…
The paper introduces Clover, a code completion tool that logs students' interactions and offers attention checks to promote reflective engagement during programming tasks.
The paper conducts an empirical evaluation of automated vulnerability detection tools across multiple software ecosystems using a curated ground-truth dataset derived from OSV, highlighting systematic…