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)

1,681 to 1,740 of 2,794

daVinci-Dev: Agent-native Mid-training for Software Engineering
Ji Zeng, Dayuan Fu, Tiantian Mi +14
cs.SEcs.AIarXiv:2601.18418v22026
BugsInPy: A Database of Existing Bugs in Python Programs to Enable Controlled Testing and Debugging Studies
Ratnadira Widyasari, Sheng Qin Sim, Camellia Lok +13
cs.SEarXiv:2401.15481v12024
How does information access affect LLM monitors' ability to detect sabotage?
Rauno Arike, Raja Mehta Moreno, Rohan Subramani +2
cs.AIcs.SEarXiv:2601.21112v22026
The Impact of Class Rebalancing Techniques on the Performance and Interpretation of Defect Prediction Models
Chakkrit Tantithamthavorn, Ahmed E. Hassan, Kenichi Matsumoto
cs.SEarXiv:1801.10269v12018
UML Class Diagram Evaluation and Repair Strategies based on LLMs
Jie Liang, Peng Liang, Chong Wang
cs.SEarXiv:2608.28800v12026
LineVD: Statement-level Vulnerability Detection using Graph Neural Networks
David Hin, Andrey Kan, Huaming Chen +1
cs.CRcs.SEarXiv:2203.05181v22022
LocAgent: Graph-Guided LLM Agents for Code Localization
Zhaoling Chen, Xiangru Tang, Gangda Deng +6
cs.SEcs.AIcs.CLarXiv:2503.09089v22025
Exploring LLM-based Agents for Root Cause Analysis
Devjeet Roy, Xuchao Zhang, Rashi Bhave +4
cs.SEcs.CLcs.LGarXiv:2403.04123v12024
CodeMem: Architecting Reproducible Agents via Dynamic MCP and Procedural Memory
Nishant Gaurav, Adit Akarsh, Tejas Ravishankar +1
cs.SEcs.AIarXiv:2512.15813v12025
Benchmarking Reward Hack Detection in Code Environments via Contrastive Analysis
Darshan Deshpande, Anand Kannappan, Rebecca Qian
cs.SEcs.AIcs.LGarXiv:2601.20103v12026
Red teaming ChatGPT via Jailbreaking: Bias, Robustness, Reliability and Toxicity
Terry Yue Zhuo, Yujin Huang, Chunyang Chen +1
cs.CLcs.SEarXiv:2301.12867v42023
From Evidence to Effect: Authority Semantics and Runtime Infrastructure for Stateful Agents
Yang Li, Zongsi Xu, Sergey Volkov +7
cs.MAcs.SEarXiv:2609.08472v32026
Self-planning Code Generation with Large Language Models
Xue Jiang, Yihong Dong, Lecheng Wang +5
cs.SEarXiv:2303.06689v52023
Code Smells and Refactoring: A Tertiary Systematic Review of Challenges and Observations
Guilherme Lacerda, Fabio Petrillo, Marcelo Pimenta +1
cs.SEarXiv:2004.10777v12020
Characterizing the Landscape of Open-Source Satellite Software
Jinfeng Wen, Qi Liang, Yuehan Sun +4
cs.SEarXiv:2608.26211v12026
CodeAgent: Autonomous Communicative Agents for Code Review
Xunzhu Tang, Kisub Kim, Yewei Song +6
cs.SEarXiv:2402.02172v52024
How Effective are Smart Contract Analysis Tools? Evaluating Smart Contract Static Analysis Tools Using Bug Injection
Asem Ghaleb, Karthik Pattabiraman
cs.SEarXiv:2005.11613v12020
Uncertainty-Guided Chain-of-Thought for Code Generation with LLMs
Yuqi Zhu, Ge Li, Xue Jiang +4
cs.SEarXiv:2503.15341v12025
SWE-PolyBench: A multi-language benchmark for repository level evaluation of coding agents
Muhammad Shihab Rashid, Christian Bock, Yuan Zhuang +10
cs.SEarXiv:2504.08703v32025
Authority Is Not a String: A Capability-Scoped Harness for Prompt-Injection-Resistant Coding Agents
Dimitrios Stamatios Bouras, Yihan Dai, Sergey Mechtaev
cs.SEarXiv:2609.08371v12026
Talking to Itself While Coding: What Makes Comments Help Code Generation?
Dangfeng Pan, Zhensu Sun, Cenyuan Zhang +2
cs.SEcs.AIarXiv:2609.09242v12026
Finding Faster Configurations using FLASH
Vivek Nair, Zhe Yu, Tim Menzies +2
cs.SEarXiv:1801.02175v22018
Deep Transfer Learning for Source Code Modeling
Yasir Hussain, Zhiqiu Huang, Yu Zhou +1
cs.LGcs.NEcs.SEarXiv:1910.05493v22019
Identifying Patch Correctness in Test-Based Program Repair
Yingfei Xiong, Xinyuan Liu, Muhan Zeng +2
cs.SEarXiv:1706.09120v32017
Entropy Guided Spectrum Based Bug Localization Using Statistical Language Model
Saikat Chakraborty, Yujian Li, Matt Irvine +2
cs.SEarXiv:1802.06947v12018
StateAFL: Greybox Fuzzing for Stateful Network Servers
Roberto Natella
cs.CRcs.OScs.SEarXiv:2110.06253v22021
6.5% of the Neuro-Symbolic Literature Can Be Reproduced from Its Published Artifacts, a Six-Stage Audit Framework and First Instantiation
Brandon Colelough, Vladimir Martirosyan, Ishan Tamrakar +6
cs.AIcs.SEarXiv:2608.26236v12026
Agile Software Development Methods: Review and Analysis
Pekka Abrahamsson, Outi Salo, Jussi Ronkainen +1
cs.SEarXiv:1709.08439v12017
FeedbackEval: A Benchmark for Evaluating Large Language Models in Feedback-Driven Code Repair Tasks
Dekun Dai, MingWei Liu, Anji Li +5
cs.SEarXiv:2504.06939v22025
REINS: Agent-guided Thread Scheduling for Concurrency Bug Detection and Reproduction
Yu Zhang, Corina S. Pasareanu, Guowei Yang
cs.SEarXiv:2610.13421v12026
Dockerless: Environment-Free Program Verifier for Coding Agents
Wenhao Zeng, Yuling Shi, Xiaodong Gu +10
cs.SEcs.AIarXiv:2606.28436v12026
AI-to-AI Code Reviews of GitHub Pull Requests
Niruthiha Selvanayagam, Taher A. Ghaleb
cs.SEarXiv:2608.21311v12026
StarCoder 2 and The Stack v2: The Next Generation
Anton Lozhkov, Raymond Li, Loubna Ben Allal +63
cs.SEcs.AIarXiv:2402.19173v12024
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
TestSuiteBench: Coding Agents Struggle to Generate Strong Test Suites from Specifications
Kazuki Egashira, Niels Mündler-Sasahara, Mark Niklas Müller +1
cs.SEarXiv:2610.13065v12026
TAM-Eval: Evaluating LLMs for Automated Unit Test Maintenance
Elena Bruches, Vadim Alperovich, Dari Baturova +8
cs.SEcs.AIarXiv:2601.18241v12026
One Gate Is Not Enough: Composing Stateful Pre-Action Controls for Agentic AI
Gaston Besanson
cs.SEcs.AIcs.CYarXiv:2608.18360v12026
Vulnerable Models in the AI Supply Chain: An Empirical Study of Adoption, Propagation, and Usage Patterns
The Anh Nguyen, Triet Huynh Minh Le, M. Ali Babar
cs.CRcs.SEarXiv:2610.12893v12026
Evaluation of Software Quality Through Refactoring Commit-Impact Analysis
Md Safayat Hossen, Sheikh Moonwara Anjum Monisha, Shadid Intisar Quasem
cs.SEarXiv:2610.12890v12026
DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation
Yuhang Lai, Chengxi Li, Yiming Wang +7
cs.SEcs.CLarXiv:2211.11501v12022
DPIAgent: Divide, Protocol, Isolate for Agentic Reproduction Test Generation
Hao Liu, Steven Liu, Xin Zhang +8
cs.SEarXiv:2608.23341v12026
The Alignment Problem in Constrained Code Generation
Matteo Biagiola, Jahrim Gabriele Cesario, Luca Di Grazia +2
cs.SEcs.LGcs.PLarXiv:2606.21619v12026
The Prompt Triangle: A Registered Report on Prompts as Hybrid Artifacts
Shalini Chakraborty, Jan-Philipp Steghöfer
cs.SEarXiv:2609.04209v12026
SWE-World: Building Software Engineering Agents in Docker-Free Environments
Shuang Sun, Huatong Song, Lisheng Huang +11
cs.SEcs.CLarXiv:2602.03419v12026
R2Vul: Learning to Reason about Software Vulnerabilities with Reinforcement Learning and Structured Reasoning Distillation
Martin Weyssow, Chengran Yang, Junkai Chen +12
cs.SEcs.AIcs.CLarXiv:2504.04699v22025
Separating Engineering Reasoning from DEXPI Serialization in LLM-Based Greenfield Surface-Process Design: A Three-Case Study for Underground Gas Storage
Qingchuan Zhu, Shuyue Tong, Pengju Ren
cs.SEcs.AIarXiv:2609.12656v12026
Qiushi Engine on AstaBench E2E-Bench-Hard
Wenhao Li, Shuxing Yang, Fujia Chen +13
cs.AIcs.SEarXiv:2609.08196v12026
SciReplicate-Bench: Benchmarking LLMs in Agent-driven Algorithmic Reproduction from Research Papers
Yanzheng Xiang, Hanqi Yan, Shuyin Ouyang +2
cs.CLcs.AIcs.MAarXiv:2504.00255v22025
Probabilistic Model Checking of Autoregressive Neural Sequence Models
Helge Spieker, Dennis Gross, Arnaud Gotlieb
cs.SEcs.AIarXiv:2609.00838v12026
Automated Directed Fairness Testing
Sakshi Udeshi, Pryanshu Arora, Sudipta Chattopadhyay
cs.LGcs.AIcs.SEarXiv:1807.00468v22018
TAI3: Testing Agent Integrity in Interpreting User Intent
Shiwei Feng, Xiangzhe Xu, Xuan Chen +5
cs.SEcs.AIcs.CYarXiv:2506.07524v32025
When Models Edit Too Much: On the Fidelity of Minimal Code Edits
Tongyao Zhu, Wei Hern Lim, Min-Yen Kan
cs.SEcs.AIcs.CLarXiv:2609.04061v12026
Are "Solved Issues" in SWE-bench Really Solved Correctly? An Empirical Study
You Wang, Michael Pradel, Zhongxin Liu
cs.SEarXiv:2503.15223v22025
Empirical Review of Java Program Repair Tools: A Large-Scale Experiment on 2,141 Bugs and 23,551 Repair Attempts
Thomas Durieux, Fernanda Madeiral, Matias Martinez +1
cs.SEarXiv:1905.11973v12019
AROMA+: A Study of Factors Affecting Reproducible Builds in the Maven Ecosystem
Mehdi Keshani, Amirhossein Rahmati, Mohammad Hossein Aref +1
cs.SEarXiv:2608.27125v12026
Hypothesis-Driven Skill Optimization for LLM Agents
Fangxin Shang, Yehui Yang
cs.AIcs.SEarXiv:2606.22330v12026
Evaluating Exact Output and Checkpoint-State Prediction in Real Programs
Xiaohong Chen, David Bucur, Chenglong Ma +4
cs.SEcs.AIarXiv:2610.11889v12026
Cadence: Strategic Guidance for Coding Agents
Minxing Wang, He Ye, Earl T. Barr +1
cs.SEarXiv:2610.12269v12026
Requirements-driven Test Generation for Autonomous Vehicles with Machine Learning Components
Cumhur Erkan Tuncali, Georgios Fainekos, Danil Prokhorov +2
cs.ROcs.LGcs.SEarXiv:1908.01094v12019
SkillOps: Managing LLM Agent Skill Libraries as Self-Maintaining Software Ecosystems
Hongji Pu, Xinyuan Song, Liang Zhao
cs.SEcs.MAarXiv:2605.13716v12026

Software Engineering

daVinci-Dev: Agent-native Mid-training for Software Engineering

BugsInPy: A Database of Existing Bugs in Python Programs to Enable Controlled Testing and Debugging Studies

How does information access affect LLM monitors' ability to detect sabotage?

The Impact of Class Rebalancing Techniques on the Performance and Interpretation of Defect Prediction Models

UML Class Diagram Evaluation and Repair Strategies based on LLMs

LineVD: Statement-level Vulnerability Detection using Graph Neural Networks

LocAgent: Graph-Guided LLM Agents for Code Localization

Exploring LLM-based Agents for Root Cause Analysis

CodeMem: Architecting Reproducible Agents via Dynamic MCP and Procedural Memory

Benchmarking Reward Hack Detection in Code Environments via Contrastive Analysis

Red teaming ChatGPT via Jailbreaking: Bias, Robustness, Reliability and Toxicity

From Evidence to Effect: Authority Semantics and Runtime Infrastructure for Stateful Agents

Self-planning Code Generation with Large Language Models

Code Smells and Refactoring: A Tertiary Systematic Review of Challenges and Observations

Characterizing the Landscape of Open-Source Satellite Software

CodeAgent: Autonomous Communicative Agents for Code Review

How Effective are Smart Contract Analysis Tools? Evaluating Smart Contract Static Analysis Tools Using Bug Injection

Uncertainty-Guided Chain-of-Thought for Code Generation with LLMs

SWE-PolyBench: A multi-language benchmark for repository level evaluation of coding agents

Authority Is Not a String: A Capability-Scoped Harness for Prompt-Injection-Resistant Coding Agents

Talking to Itself While Coding: What Makes Comments Help Code Generation?

Finding Faster Configurations using FLASH

Deep Transfer Learning for Source Code Modeling

Identifying Patch Correctness in Test-Based Program Repair

Entropy Guided Spectrum Based Bug Localization Using Statistical Language Model

StateAFL: Greybox Fuzzing for Stateful Network Servers

6.5% of the Neuro-Symbolic Literature Can Be Reproduced from Its Published Artifacts, a Six-Stage Audit Framework and First Instantiation

Agile Software Development Methods: Review and Analysis

FeedbackEval: A Benchmark for Evaluating Large Language Models in Feedback-Driven Code Repair Tasks

REINS: Agent-guided Thread Scheduling for Concurrency Bug Detection and Reproduction

Dockerless: Environment-Free Program Verifier for Coding Agents

AI-to-AI Code Reviews of GitHub Pull Requests

StarCoder 2 and The Stack v2: The Next Generation

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

TestSuiteBench: Coding Agents Struggle to Generate Strong Test Suites from Specifications

TAM-Eval: Evaluating LLMs for Automated Unit Test Maintenance

One Gate Is Not Enough: Composing Stateful Pre-Action Controls for Agentic AI

Vulnerable Models in the AI Supply Chain: An Empirical Study of Adoption, Propagation, and Usage Patterns

Evaluation of Software Quality Through Refactoring Commit-Impact Analysis

DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation

DPIAgent: Divide, Protocol, Isolate for Agentic Reproduction Test Generation

The Alignment Problem in Constrained Code Generation

The Prompt Triangle: A Registered Report on Prompts as Hybrid Artifacts

SWE-World: Building Software Engineering Agents in Docker-Free Environments

R2Vul: Learning to Reason about Software Vulnerabilities with Reinforcement Learning and Structured Reasoning Distillation

Separating Engineering Reasoning from DEXPI Serialization in LLM-Based Greenfield Surface-Process Design: A Three-Case Study for Underground Gas Storage

Qiushi Engine on AstaBench E2E-Bench-Hard

SciReplicate-Bench: Benchmarking LLMs in Agent-driven Algorithmic Reproduction from Research Papers

Probabilistic Model Checking of Autoregressive Neural Sequence Models

Automated Directed Fairness Testing

TAI3: Testing Agent Integrity in Interpreting User Intent

When Models Edit Too Much: On the Fidelity of Minimal Code Edits

Are "Solved Issues" in SWE-bench Really Solved Correctly? An Empirical Study

Empirical Review of Java Program Repair Tools: A Large-Scale Experiment on 2,141 Bugs and 23,551 Repair Attempts

AROMA+: A Study of Factors Affecting Reproducible Builds in the Maven Ecosystem

Hypothesis-Driven Skill Optimization for LLM Agents

Evaluating Exact Output and Checkpoint-State Prediction in Real Programs

Cadence: Strategic Guidance for Coding Agents

Requirements-driven Test Generation for Autonomous Vehicles with Machine Learning Components

SkillOps: Managing LLM Agent Skill Libraries as Self-Maintaining Software Ecosystems