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)

1 to 60 of 1,389

Owl Eyes: Spotting UI Display Issues via Visual Understanding
Zhe Liu, Chunyang Chen, Junjie Wang +3
cs.SEarXiv:2009.01417v22020
Learning Performance-Improving Code Edits
Alexander Shypula, Aman Madaan, Yimeng Zeng +7
cs.SEcs.AIcs.LGarXiv:2302.07867v52023
Verus-SpecGym: An Agentic Environment for Evaluating Specification Autoformalization
Anmol Agarwal, Natalie Neamtu, Pranjal Aggarwal +6
cs.SEcs.AIcs.CLarXiv:2605.26457v12026
TBar: Revisiting Template-based Automated Program Repair
Kui Liu, Anil Koyuncu, Dongsun Kim +1
cs.SEarXiv:1903.08409v22019
VLAA-GUI: Knowing When to Stop, Recover, and Search, A Modular Framework for GUI Automation
Qijun Han, Haoqin Tu, Zijun Wang +11
cs.CLcs.AIcs.SEarXiv:2604.21375v22026
Scaling Test-Time Compute for Agentic Coding
Joongwon Kim, Wannan Yang, Kelvin Niu +13
cs.SEcs.AIcs.CLarXiv:2604.16529v12026
Log-based Anomaly Detection Without Log Parsing
Van-Hoang Le, Hongyu Zhang
cs.SEcs.AIarXiv:2108.01955v32021
Developer Attitudes and Practices Towards Optimizing Software Energy Consumption
Max Weber, Alina Mailach, Florian Sattler +2
cs.SEarXiv:2608.30527v12026
FuzzingBrain-Bench V1: Evaluating Open-Ended Bug Discovery by LLMs
Ze Sheng, Aleksandar Kezic, Zhicheng Chen +1
cs.AIcs.CRcs.LGarXiv:2608.25158v12026
Secret MCP: Evidence-Bounded and Context-Isolated Design Specification Generation from Web Screenshots
Yeongjin Jo
cs.SEarXiv:2608.24944v12026
What is Wrong with Topic Modeling? (and How to Fix it Using Search-based Software Engineering)
Amritanshu Agrawal, Wei Fu, Tim Menzies
cs.SEcs.AIcs.CLarXiv:1608.08176v42016
MemGovern: Enhancing Code Agents through Learning from Governed Human Experiences
Qihao Wang, Ziming Cheng, Shuo Zhang +12
cs.SEcs.AIarXiv:2601.06789v22026
Repo0: Design-Driven Zero-to-All Code Generation
Silin Chen, Haoyi Teng, Xiaodong Gu +5
cs.SEcs.AIarXiv:2608.19854v12026
A Comparative Study of Programming Languages in Rosetta Code
Sebastian Nanz, Carlo A. Furia
cs.SEarXiv:1409.0252v42014
Flama: a Python framework for development and deployment of production-ready APIs, machine learning, and LLM services
José A. Perdiguero López, Miguel A. Durán-Olivencia
cs.SEcs.AIcs.LGarXiv:2608.18733v12026
GraphCodeBERT: Pre-training Code Representations with Data Flow
Daya Guo, Shuo Ren, Shuai Lu +15
cs.SEcs.CLarXiv:2009.08366v42020
The Quality of Claude AI-authored Python Tests Is Not Weaker Than Human-authored Tests
Douglas J. Leith
cs.SEcs.AIarXiv:2608.15188v12026
SWE-Pruner Pro: The Coder LLM Already Knows What to Prune
Yuhang Wang, Yuling Shi, Shaoqiu Zhang +6
cs.CLcs.SEarXiv:2607.18213v12026
SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering
John Yang, Carlos E. Jimenez, Alexander Wettig +4
cs.SEcs.AIcs.CLarXiv:2405.15793v32024
SyGuS-Comp 2016: Results and Analysis
Rajeev Alur, Dana Fisman, Rishabh Singh +1
cs.SEcs.LGcs.LOarXiv:1611.07627v12016
Proof-or-Stop: Don't Trust the Agent, Trust the Evidence -- Loop Engineering for Verifiable Evidence-Gated Lifecycle Control
Jek Huang, Jeffery Hsia, Jiayi Sun +3
cs.AIcs.SEarXiv:2607.14890v12026
Don't Complete It! Preventing Unhelpful Code Completion for Productive and Sustainable Neural Code Completion Systems
Zhensu Sun, Xiaoning Du, Fu Song +4
cs.SEcs.AIarXiv:2209.05948v32022
When to Show a Suggestion? Integrating Human Feedback in AI-Assisted Programming
Hussein Mozannar, Gagan Bansal, Adam Fourney +1
cs.HCcs.LGcs.SEarXiv:2306.04930v32023
Summaries:한국어
Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training
Evan Hubinger, Carson Denison, Jesse Mu +36
cs.CRcs.AIcs.CLarXiv:2401.05566v32024
An Analysis of the Automatic Bug Fixing Performance of ChatGPT
Dominik Sobania, Martin Briesch, Carol Hanna +1
cs.SEarXiv:2301.08653v12023
Minimal Prompt Perturbations Lead to Code Vulnerabilities: Prompt Fragility and Hidden-State Signals in Coding LLMs
Alexander Sternfeld, Andrei Kucharavy, Ljiljana Dolamic
cs.CRcs.CLcs.SEarXiv:2605.29737v12026
A Study on the Impact of Natural Language Differences in Prompts on Automatic Code Generation Using LLMs
Haruka Tokumasu, Masanari Kondo, Alexander Serebrenik +5
cs.SEarXiv:2609.18311v12026
MVD: Memory-Related Vulnerability Detection Based on Flow-Sensitive Graph Neural Networks
Sicong Cao, Xiaobing Sun, Lili Bo +3
cs.CRcs.SEarXiv:2203.02660v12022
Search-Based Metamorphic Testing of Vision-Language Models in Autonomous Underwater Robotic Software
Muhammad Yousaf, Aitor Arrieta, Shaukat Ali +2
cs.SEarXiv:2609.17007v12026
A Case-Bundle Operating Model for Coding Agents in OpenFOAM-Based CFD
Ke Xiao, Han Li, Teng Zhang +3
cs.SEcs.CEcs.DCarXiv:2609.11941v12026
Models as Governed Interfaces for AI-Native MBSE: Read-Side Adequacy and Write-Side Admissibility
Jason Gower, Michael J. de C. Henshaw, Siyuan Ji
cs.SEcs.AIarXiv:2609.16252v12026
An Exploratory Study of Dependabot Cooldown Adoption in Open-Source GitHub Projects
Hidetake Tanaka, Rikuto Tsuchida, Kazumasa Shimari +2
cs.SEarXiv:2609.16605v12026
Intelligent Semantic Matching (ISM) for Video Tutorial Search using Transformer Models
Ahmad J. Tayeb, Sonia Haiduc
cs.SEarXiv:2609.12921v12026
AI Policies: Help or Hindrance? A Software Developer's Perspective
Samuel Ferino, Rashina Hoda, John Grundy +2
cs.SEcs.AIarXiv:2609.16496v12026
Towards an Asset Administration Shell Maturity Model
Carsten Ellwein, David Dietrich, Rozana Cvitkovic +1
cs.SEeess.SYarXiv:2609.17084v12026
MaRDMO: FAIR Documentation of In-Silico Research
Marco Reidelbach, Marcus Weber
cs.DLcs.SEarXiv:2609.11931v12026
Natural-Language to SysMLv2 Translation via Conformance-Driven Iterative Refinement
Chance LaVoie, Eladio Andujar Lugo, Taylan G. Topcu +1
cs.SEcs.AIarXiv:2607.14162v12026
FrontierCS: Evolving Challenges for Evolving Intelligence
Qiuyang Mang, Wenhao Chai, Zhifei Li +48
cs.LGcs.SEarXiv:2512.15699v12025
Type-IV Code Clone Detection via Layer-Wise Non-Contrastive Representation Learning
Luciano Marchezan, Kevin Delcourt, Eugene Syriani +1
cs.SEcs.LGarXiv:2609.17338v12026
Guidelines for the Search Strategy to Update Systematic Literature Reviews in Software Engineering
Claes Wohlin, Emilia Mendes, Katia Romero Felizardo +1
cs.SEarXiv:2006.05542v12020
SkillMOO: Multi-Objective Optimization of Agent Skills for Software Engineering
Jingzhi Gong, Ruizhen Gu, Zhiwei Fei +7
cs.SEcs.AIarXiv:2604.09297v32026
How Coding Agents Fail Their Users: A Large-Scale Analysis of Developer-Agent Misalignment in 20,574 Real-World Sessions
Ningzhi Tang, Chaoran Chen, Gelei Xu +5
cs.SEcs.AIcs.HCarXiv:2605.29442v22026
Agentic Memory Enhanced Recursive Reasoning for Root Cause Localization in Microservices
Lingzhe Zhang, Tong Jia, Yunpeng Zhai +5
cs.SEcs.AIarXiv:2601.02732v12026
FixMiner: Mining Relevant Fix Patterns for Automated Program Repair
Anil Koyuncu, Kui Liu, Tegawendé F. Bissyandé +4
cs.SEarXiv:1810.01791v22018
Sorting and Transforming Program Repair Ingredients via Deep Learning Code Similarities
Martin White, Michele Tufano, Matias Martinez +2
cs.SEarXiv:1707.04742v22017
Continuous Integration, Delivery and Deployment: A Systematic Review on Approaches, Tools, Challenges and Practices
Mojtaba Shahin, Muhammad Ali Babar, Liming Zhu
cs.SEarXiv:1703.07019v12017
A Survey of Smart Contract Formal Specification and Verification
Palina Tolmach, Yi Li, Shang-Wei Lin +2
cs.SEarXiv:2008.02712v32020
Learn&Fuzz: Machine Learning for Input Fuzzing
Patrice Godefroid, Hila Peleg, Rishabh Singh
cs.AIcs.CRcs.LGarXiv:1701.07232v12017
The BrowserGym Ecosystem for Web Agent Research
Thibault Le Sellier De Chezelles, Maxime Gasse, Alexandre Drouin +17
cs.LGcs.AIcs.SEarXiv:2412.05467v42024
Lie to Me: Finding Bugs in ZK DSL Toolchains with Adversarial Witness Injection
Sebastian Watzinger, Christoph Hochrainer, Valentin Wüstholz +1
cs.CRcs.SEarXiv:2608.30648v12026
ChatDev: Communicative Agents for Software Development
Chen Qian, Wei Liu, Hongzhang Liu +11
cs.SEcs.CLcs.MAarXiv:2307.07924v52023
FoldKit: A Python library for efficient storage and retrieval of co-folding predictions
Jonathan A. Levine, Melissa Pathil, Samuel Nitz +2
q-bio.QMcs.SEarXiv:2608.28788v12026
Operationalizing Regulations into Code: A Model to Enhance Governance and Compliance in LLM Selection for Software Engineering
Jonysberg Quintino, Hermano Moura, Filipe Calegário
cs.SEarXiv:2608.27703v12026
MemToC: Benchmarking Memory-Tool Conflict Resolution in Large Language Models
Arseniy Varlamov, Rishat Zinnatullin, Elisei Rykov +2
cs.CLcs.AIcs.MAarXiv:2608.26295v12026
From Natural Language Requirements to Graphical User Interfaces: Automated Prototyping and Verification with Pretrained Language Models
Kristian Kolthoff
cs.SEarXiv:2608.24749v12026
On the Use of Deep Learning in Software Defect Prediction
Görkem Giray, Kwabena Ebo Bennin, Ömer Köksal +2
cs.SEarXiv:2210.02236v12022
Causal Inference-Based Root Cause Analysis for Online Service Systems with Intervention Recognition
Mingjie Li, Zeyan Li, Kanglin Yin +4
cs.SEcs.AIarXiv:2206.05871v12022
Getafix: Learning to Fix Bugs Automatically
Johannes Bader, Andrew Scott, Michael Pradel +1
cs.SEarXiv:1902.06111v52019
Leveraging Automated Unit Tests for Unsupervised Code Translation
Baptiste Roziere, Jie M. Zhang, Francois Charton +3
cs.SEcs.CLcs.LGarXiv:2110.06773v22021
AgentCompass: A Unified Evaluation Infrastructure for Agent Capabilities
Kai Chen, Zichen Ding, Jiaye Ge +20
cs.AIcs.SEarXiv:2607.13705v32026

Software Engineering

Owl Eyes: Spotting UI Display Issues via Visual Understanding

Learning Performance-Improving Code Edits

Verus-SpecGym: An Agentic Environment for Evaluating Specification Autoformalization

TBar: Revisiting Template-based Automated Program Repair

VLAA-GUI: Knowing When to Stop, Recover, and Search, A Modular Framework for GUI Automation

Scaling Test-Time Compute for Agentic Coding

Log-based Anomaly Detection Without Log Parsing

Developer Attitudes and Practices Towards Optimizing Software Energy Consumption

FuzzingBrain-Bench V1: Evaluating Open-Ended Bug Discovery by LLMs

Secret MCP: Evidence-Bounded and Context-Isolated Design Specification Generation from Web Screenshots

What is Wrong with Topic Modeling? (and How to Fix it Using Search-based Software Engineering)

MemGovern: Enhancing Code Agents through Learning from Governed Human Experiences

Repo0: Design-Driven Zero-to-All Code Generation

A Comparative Study of Programming Languages in Rosetta Code

Flama: a Python framework for development and deployment of production-ready APIs, machine learning, and LLM services

GraphCodeBERT: Pre-training Code Representations with Data Flow

The Quality of Claude AI-authored Python Tests Is Not Weaker Than Human-authored Tests

SWE-Pruner Pro: The Coder LLM Already Knows What to Prune

SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering

SyGuS-Comp 2016: Results and Analysis

Proof-or-Stop: Don't Trust the Agent, Trust the Evidence -- Loop Engineering for Verifiable Evidence-Gated Lifecycle Control

Don't Complete It! Preventing Unhelpful Code Completion for Productive and Sustainable Neural Code Completion Systems

When to Show a Suggestion? Integrating Human Feedback in AI-Assisted Programming

Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training

An Analysis of the Automatic Bug Fixing Performance of ChatGPT

Minimal Prompt Perturbations Lead to Code Vulnerabilities: Prompt Fragility and Hidden-State Signals in Coding LLMs

A Study on the Impact of Natural Language Differences in Prompts on Automatic Code Generation Using LLMs

MVD: Memory-Related Vulnerability Detection Based on Flow-Sensitive Graph Neural Networks

Search-Based Metamorphic Testing of Vision-Language Models in Autonomous Underwater Robotic Software

A Case-Bundle Operating Model for Coding Agents in OpenFOAM-Based CFD

Models as Governed Interfaces for AI-Native MBSE: Read-Side Adequacy and Write-Side Admissibility

An Exploratory Study of Dependabot Cooldown Adoption in Open-Source GitHub Projects

Intelligent Semantic Matching (ISM) for Video Tutorial Search using Transformer Models

AI Policies: Help or Hindrance? A Software Developer's Perspective

Towards an Asset Administration Shell Maturity Model

MaRDMO: FAIR Documentation of In-Silico Research

Natural-Language to SysMLv2 Translation via Conformance-Driven Iterative Refinement

FrontierCS: Evolving Challenges for Evolving Intelligence

Type-IV Code Clone Detection via Layer-Wise Non-Contrastive Representation Learning

Guidelines for the Search Strategy to Update Systematic Literature Reviews in Software Engineering

SkillMOO: Multi-Objective Optimization of Agent Skills for Software Engineering

How Coding Agents Fail Their Users: A Large-Scale Analysis of Developer-Agent Misalignment in 20,574 Real-World Sessions

Agentic Memory Enhanced Recursive Reasoning for Root Cause Localization in Microservices

FixMiner: Mining Relevant Fix Patterns for Automated Program Repair

Sorting and Transforming Program Repair Ingredients via Deep Learning Code Similarities

Continuous Integration, Delivery and Deployment: A Systematic Review on Approaches, Tools, Challenges and Practices

A Survey of Smart Contract Formal Specification and Verification

Learn&Fuzz: Machine Learning for Input Fuzzing

The BrowserGym Ecosystem for Web Agent Research

Lie to Me: Finding Bugs in ZK DSL Toolchains with Adversarial Witness Injection

ChatDev: Communicative Agents for Software Development

FoldKit: A Python library for efficient storage and retrieval of co-folding predictions

Operationalizing Regulations into Code: A Model to Enhance Governance and Compliance in LLM Selection for Software Engineering

MemToC: Benchmarking Memory-Tool Conflict Resolution in Large Language Models

From Natural Language Requirements to Graphical User Interfaces: Automated Prototyping and Verification with Pretrained Language Models

On the Use of Deep Learning in Software Defect Prediction

Causal Inference-Based Root Cause Analysis for Online Service Systems with Intervention Recognition

Getafix: Learning to Fix Bugs Automatically

Leveraging Automated Unit Tests for Unsupervised Code Translation

AgentCompass: A Unified Evaluation Infrastructure for Agent Capabilities