Software Engineering

Papers filed under cs.SE on arXiv, each one already summarized by Paperlayer. Open any of them to read the summary beside the original PDF, with every point linked to the line, figure, or table it came from.

Search paper metadata (including unsummarized papers)

61 to 120 of 1,389

Identifying Implementation Bugs in Machine Learning based Image Classifiers using Metamorphic Testing
Anurag Dwarakanath, Manish Ahuja, Samarth Sikand +4
cs.SEcs.LGarXiv:1808.05353v12018
Practical Program Repair via Bytecode Mutation
Ali Ghanbari, Lingming Zhang
cs.SEarXiv:1807.03512v12018
Measuring Coding Challenge Competence With APPS
Dan Hendrycks, Steven Basart, Saurav Kadavath +8
cs.SEcs.CLcs.LGarXiv:2105.09938v32021
ATIBA: Grounded Integrity and Quality Checking for Research Papers
Veli Karakaya, Semih Çağlar, Yusuf Yiğit Korkmaz +1
cs.SEarXiv:2609.04123v12026
SpikingJelly: An open-source machine learning infrastructure platform for spike-based intelligence
Wei Fang, Yanqi Chen, Jianhao Ding +7
cs.NEcs.LGcs.SEarXiv:2310.16620v12023
Virtual Testing of Automated Driving Systems through Credible Simulations
Riccardo Dona, Espedito Rusciano, Biagio Ciuffo
cs.ROcs.SEarXiv:2609.03760v12026
AI Harness Engineering: A Runtime Substrate for Foundation-Model Software Agents
Hailin Zhong, Shengxin Zhu
cs.SEcs.AIarXiv:2605.13357v12026
Agentic Refactoring: An Empirical Study of AI Coding Agents
Kosei Horikawa, Hao Li, Yutaro Kashiwa +3
cs.SEarXiv:2511.04824v12025
RefDiff: Detecting Refactorings in Version Histories
Danilo Silva, Marco Tulio Valente
cs.SEarXiv:1704.01544v12017
CodeScore: Evaluating Code Generation by Learning Code Execution
Yihong Dong, Jiazheng Ding, Xue Jiang +3
cs.SEarXiv:2301.09043v42023
Can AI Remediate Backend Failures Safely? GuardedAct with Blast-Radius-Aware Sandboxing
Wanrong Cai, Tianyu Yu, Shaorui Pi +2
cs.DCcs.SEarXiv:2609.11264v12026
SemVerBench: Benchmarking LLM Comprehension of Version-Constraint Resolution Semantics
Qibai Chen, Zeming Liu
cs.AIcs.SEarXiv:2609.11180v12026
BenchShield: Formal Model-Backed Instrumentation for Reward Integrity in LLM-Agent Evaluation Infrastructure
Shenghan Zheng, Zonglin Di, Yimin Liu +19
cs.CRcs.AIcs.SEarXiv:2609.11028v12026
Summaries:한국어
Grounding Agent Memory: Environment-Probing Curation for Enterprise Agents
Susheel Suresh, Hazel Mak, Sahil Bhatnagar +2
cs.AIcs.SEarXiv:2609.11060v12026
Decoupling Readiness from Release for Tail-Aware Scheduling of Agentic LLM Workflows
Bochao Feng, Jianjiang Li, Haojie Wang +4
cs.AIcs.SEarXiv:2609.10964v12026
DeFiFusion: Combining Transaction Events with Smart Contracts to Detect Price Manipulation Attacks
Rui Cao, Shaojing Fan, Liming Fang +3
cs.CRcs.AIcs.SEarXiv:2609.11008v12026
AspisAI: A Canonical, Machine-Interpretable Governance Framework for Automated Multi-Standard Compliance Monitoring
Tsafac Nkombong Regine Cyrille, Hasan Dag, Reiner Creutzburg +1
cs.CRcs.CYcs.SEarXiv:2609.10881v12026
An analysis of the relationship of input metrics
Addison Crump
cs.SEcs.FLarXiv:2609.11824v12026
Beyond Static Guarantees: Measuring the Static-Pass Dynamic-Fail Gap in Security-Sensitive and LLM-Generated Python Code
Jessica Pourleyli, Maitreyee Das Urmi, Glaucia Melo
cs.CRcs.AIcs.SEarXiv:2609.10762v12026
A2ABreak: Systematic Security Analysis of the A2A Protocol
Alireza Lotfi, Mirza Masfiqur Rahman, Imtiaz Karim +1
cs.CRcs.SEarXiv:2609.10871v12026
Towards a Deterministic Math Solver for Clinical Language Models
Felipe Ocampo Osorio, Sebastián Andrés Cajas Ordoñez, Maximin Lange +5
cs.AIcs.SEarXiv:2609.10728v12026
Reproducibility in the Age of Agentic AI: Context Engineering at the Timescale of a Codebase
Lorena A. Barba
cs.SEcs.CYarXiv:2609.11728v12026
PRISMA-LLM: An Empirical Reporting Framework for AI-Assisted Systematic Reviews
Miguel Zabaleta, Baihan Lin
cs.SEarXiv:2609.11559v12026
Agent-Integrated Software: Interaction Contracts and Continuous Assurance
Shengcheng Yu, Chunrong Fang, Zhenyu Chen
cs.SEcs.AIarXiv:2609.11381v12026
Deep Learning-based Bug Triage System
Sourabh Pal
cs.SEarXiv:2609.11420v12026
ChurnBench: A Drift-Aware Benchmark Demonstrating That Refresh Scheduling, Not Cache Age, Governs Staleness in Agentic AI
Vivek Kumar Singh, Preeti Priyam
cs.SEarXiv:2609.11515v12026
Ecdysis: Efficient and Effective Training of Runtime Harnesses for LLM Agents
Ruiqing Yue, Yu Cui, Zhuoyu Sun +11
cs.SEcs.AIarXiv:2609.11677v12026
TripleBound: Triplet-Guided Heterogeneous Graph Learning for Microservice Decomposition
Mineth Weerasinghe, Himindu Kularathne, Methmini Madhushika +4
cs.SEarXiv:2609.11212v12026
A Model-Centric DevOps Architecture for DEVS-Based Digital Twin Simulation Services
Arnis Lektauers, Gusts Linkevičs, Guntis Mosāns +2
cs.SEcs.CEcs.DCarXiv:2609.11122v12026
CoSTAR: Data Synthesis-Driven Constraint-Aware COBOL Section Summarization for Legacy System Modernization
Hao Lin, He Jiang, Xiaochen Li +4
cs.SEarXiv:2609.11332v12026
FST Pay: Deterministic Safety-Gated Architecture for Youth Digital Payments
Shaikh Mohammed Burhan, Syed Farhaan Quadri, Tabassum Nahid Sultana
cs.SEcs.CRarXiv:2609.11195v12026
Exploring the Role of Security Experience and ChatGPT Usage Strategies on Secure Software Engineering Education
Alessio Ferrari, Minh An Nguyen, Kushal Ramkumar +1
cs.SEarXiv:2609.11303v12026
SaltBench: A Referee-Gated Protocol for Measuring Method Effects in Machine-Checked Software Work
Jason Hickey
cs.SEcs.LOarXiv:2609.11076v12026
RCL: A Retrieval-Confidence Layer for Detecting Insufficient Context in Enterprise Retrieval-Augmented Code Generation
Chandra Mohan Ravuri
cs.SEarXiv:2609.11023v12026
Engineering Reliable Commit Gates for Agentic AI: Cost-Aware Verification Portfolios under Common-Mode Data Failures
Zihao Zheng, Baichuan Li, Junyi Yao +1
cs.SEarXiv:2609.10969v12026
What a Random Draw from the MCP Registry Contains, and What Tool-Use Benchmarks Contain Instead
Haseeb Mohammed Afsar
cs.SEcs.AIarXiv:2609.10962v12026
LLMVul: A Vulnerability-Labeled Dataset of LLM-Generated C/C++ Functions from Real Production Repositories
Mohammad Farhad, Shuvalaxmi Dass
cs.SEarXiv:2609.10945v12026
When Passing Tests Hides Vulnerabilities: An Empirical Study of Silent Failures in Agentic Systems
Wenji Bai, Muhammad Waseem, Zeeshan Rasheed +2
cs.SEcs.CRarXiv:2609.10548v12026
Generative AI for trustworthy systems - Towards a health check model
Jan Bosch, Rick Kazman, Henry Muccini +1
cs.SEarXiv:2609.10595v12026
ReqEvolve: User-Oriented Software Self-Evolution through Automatic Requirement Interpretation
Md Asif Iqbal Fahim, Alessio Ferrari
cs.SEarXiv:2609.10590v12026
Governed Human-AI Prioritization Under Uncertainty: Adaptive Estimation and Dependency-Constrained Portfolio Selection
Azzeddine Ihsine, Sara Ihsine
cs.SEarXiv:2609.10648v12026
AI Safety: Not Optional, Not Later
Qinghua Lu, Yoshua Bengio
cs.SEarXiv:2609.10630v12026
Agent READMEs: An Empirical Study of Context Files for Agentic Coding
Worawalan Chatlatanagulchai, Hao Li, Yutaro Kashiwa +8
cs.SEarXiv:2511.12884v22025
VeriGuard: Enhancing LLM Agent Safety via Verified Code Generation
Lesly Miculicich, Mihir Parmar, Hamid Palangi +4
cs.SEcs.AIcs.CRarXiv:2510.05156v12025
SWE-QA: Can Language Models Answer Repository-level Code Questions?
Weihan Peng, Yuling Shi, Yuhang Wang +3
cs.CLcs.PLcs.SEarXiv:2509.14635v22025
SWE-EVO: Benchmarking Coding Agents in Long-Horizon Software Evolution Scenarios
Tue Le, Minh V. T. Thai, Dung Nguyen Manh +2
cs.SEcs.AIcs.MAarXiv:2512.18470v62025
LongCodeZip: Compress Long Context for Code Language Models
Yuling Shi, Yichun Qian, Hongyu Zhang +2
cs.CLcs.SEarXiv:2510.00446v12025
Numbat: Building and Verifying a Self-Contained Machine-Learning Stack
Thang Tran, Lan Dang
cs.SEcs.LGarXiv:2609.10632v12026
Finding Faster Configurations using FLASH
Vivek Nair, Zhe Yu, Tim Menzies +2
cs.SEarXiv:1801.02175v22018
On the Relation between Code Quality and Machine Learning Performance: A Large-scale Empirical Study
Marius Mignard, Steven Costiou, Anne Etien
cs.SEcs.LGarXiv:2609.10610v12026
Optimizing AI Inference Across the Deployment Stack
Tejinder Singh, John Pflueger, Jeebak Mitra +3
cs.SEcs.LGarXiv:2609.10550v12026
What Makes a Good LLM Agent for Real-world Penetration Testing?
Gelei Deng, Yi Liu, Yuekang Li +5
cs.CRcs.SEarXiv:2602.17622v12026
DeFiFlowBench: Benchmarking and Improving Safe Executability in Natural-Language DeFi Workflow Synthesis
Abhinav Rajeev Kumar, Harshit Arora, Varun Singh +1
cs.LGcs.SEarXiv:2609.11504v12026
Estimating Inconsistency Response Surfaces under Uncertainty in Cyber-Physical System Development
Johannes Mäkelburg, Tim Schwabe, Maribel Acosta
cs.LGcs.SEeess.SYarXiv:2609.11331v12026
Exploring LLM-based Agents for Root Cause Analysis
Devjeet Roy, Xuchao Zhang, Rashi Bhave +4
cs.SEcs.CLcs.LGarXiv:2403.04123v12024
DR-LabStack: Design and Implementation of a Clinician-Facing Web System for Diabetic Retinopathy Prediction
Yingfan Xu, Tieming Liu, Ye Liang
cs.LGcs.SEarXiv:2609.10796v12026
DIRE: A Neural Approach to Decompiled Identifier Naming
Jeremy Lacomis, Pengcheng Yin, Edward J. Schwartz +4
cs.SEarXiv:1909.09029v22019
LLM-Based Test-Driven Interactive Code Generation: User Study and Empirical Evaluation
Sarah Fakhoury, Aaditya Naik, Georgios Sakkas +2
cs.SEarXiv:2404.10100v22024
Predictors of Well-being and Productivity among Software Professionals during the COVID-19 Pandemic -- A Longitudinal Study
Daniel Russo, Paul H. P. Hanel, Seraphina Altnickel +1
cs.CYcs.SEarXiv:2007.12580v42020
An Analysis of ISO 26262: Using Machine Learning Safely in Automotive Software
Rick Salay, Rodrigo Queiroz, Krzysztof Czarnecki
cs.AIcs.LGcs.SEarXiv:1709.02435v12017

Software Engineering

Identifying Implementation Bugs in Machine Learning based Image Classifiers using Metamorphic Testing

Practical Program Repair via Bytecode Mutation

Measuring Coding Challenge Competence With APPS

ATIBA: Grounded Integrity and Quality Checking for Research Papers

SpikingJelly: An open-source machine learning infrastructure platform for spike-based intelligence

Virtual Testing of Automated Driving Systems through Credible Simulations

AI Harness Engineering: A Runtime Substrate for Foundation-Model Software Agents

Agentic Refactoring: An Empirical Study of AI Coding Agents

RefDiff: Detecting Refactorings in Version Histories

CodeScore: Evaluating Code Generation by Learning Code Execution

Can AI Remediate Backend Failures Safely? GuardedAct with Blast-Radius-Aware Sandboxing

SemVerBench: Benchmarking LLM Comprehension of Version-Constraint Resolution Semantics

BenchShield: Formal Model-Backed Instrumentation for Reward Integrity in LLM-Agent Evaluation Infrastructure

Grounding Agent Memory: Environment-Probing Curation for Enterprise Agents

Decoupling Readiness from Release for Tail-Aware Scheduling of Agentic LLM Workflows

DeFiFusion: Combining Transaction Events with Smart Contracts to Detect Price Manipulation Attacks

AspisAI: A Canonical, Machine-Interpretable Governance Framework for Automated Multi-Standard Compliance Monitoring

An analysis of the relationship of input metrics

Beyond Static Guarantees: Measuring the Static-Pass Dynamic-Fail Gap in Security-Sensitive and LLM-Generated Python Code

A2ABreak: Systematic Security Analysis of the A2A Protocol

Towards a Deterministic Math Solver for Clinical Language Models

Reproducibility in the Age of Agentic AI: Context Engineering at the Timescale of a Codebase

PRISMA-LLM: An Empirical Reporting Framework for AI-Assisted Systematic Reviews

Agent-Integrated Software: Interaction Contracts and Continuous Assurance

Deep Learning-based Bug Triage System

ChurnBench: A Drift-Aware Benchmark Demonstrating That Refresh Scheduling, Not Cache Age, Governs Staleness in Agentic AI

Ecdysis: Efficient and Effective Training of Runtime Harnesses for LLM Agents

TripleBound: Triplet-Guided Heterogeneous Graph Learning for Microservice Decomposition

A Model-Centric DevOps Architecture for DEVS-Based Digital Twin Simulation Services

CoSTAR: Data Synthesis-Driven Constraint-Aware COBOL Section Summarization for Legacy System Modernization

FST Pay: Deterministic Safety-Gated Architecture for Youth Digital Payments

Exploring the Role of Security Experience and ChatGPT Usage Strategies on Secure Software Engineering Education

SaltBench: A Referee-Gated Protocol for Measuring Method Effects in Machine-Checked Software Work

RCL: A Retrieval-Confidence Layer for Detecting Insufficient Context in Enterprise Retrieval-Augmented Code Generation

Engineering Reliable Commit Gates for Agentic AI: Cost-Aware Verification Portfolios under Common-Mode Data Failures

What a Random Draw from the MCP Registry Contains, and What Tool-Use Benchmarks Contain Instead

LLMVul: A Vulnerability-Labeled Dataset of LLM-Generated C/C++ Functions from Real Production Repositories

When Passing Tests Hides Vulnerabilities: An Empirical Study of Silent Failures in Agentic Systems

Generative AI for trustworthy systems - Towards a health check model

ReqEvolve: User-Oriented Software Self-Evolution through Automatic Requirement Interpretation

Governed Human-AI Prioritization Under Uncertainty: Adaptive Estimation and Dependency-Constrained Portfolio Selection

AI Safety: Not Optional, Not Later

Agent READMEs: An Empirical Study of Context Files for Agentic Coding

VeriGuard: Enhancing LLM Agent Safety via Verified Code Generation

SWE-QA: Can Language Models Answer Repository-level Code Questions?

SWE-EVO: Benchmarking Coding Agents in Long-Horizon Software Evolution Scenarios

LongCodeZip: Compress Long Context for Code Language Models

Numbat: Building and Verifying a Self-Contained Machine-Learning Stack

Finding Faster Configurations using FLASH

On the Relation between Code Quality and Machine Learning Performance: A Large-scale Empirical Study

Optimizing AI Inference Across the Deployment Stack

What Makes a Good LLM Agent for Real-world Penetration Testing?

DeFiFlowBench: Benchmarking and Improving Safe Executability in Natural-Language DeFi Workflow Synthesis

Estimating Inconsistency Response Surfaces under Uncertainty in Cyber-Physical System Development

Exploring LLM-based Agents for Root Cause Analysis

DR-LabStack: Design and Implementation of a Clinician-Facing Web System for Diabetic Retinopathy Prediction

DIRE: A Neural Approach to Decompiled Identifier Naming

LLM-Based Test-Driven Interactive Code Generation: User Study and Empirical Evaluation

Predictors of Well-being and Productivity among Software Professionals during the COVID-19 Pandemic -- A Longitudinal Study

An Analysis of ISO 26262: Using Machine Learning Safely in Automotive Software