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)

2,281 to 2,340 of 2,803

Towards an AI Software Factory for Data Systems
Anna Pavlenko, Bogdan Crivat, Brandon Haynes +23
cs.AIcs.DBcs.SEarXiv:2609.36323v12026
SafeLLM4SE: Statistical Evaluation and Reporting for LLM-based Software Engineering Systems
Francisco Ortin
cs.SEcs.LGarXiv:2609.37294v12026
Do Agent Benchmarks Do What They Say? An Executable-Contract Audit of Tool-Using Agent Environments
Rohith Reddy Bellibatlu, Zichong Wang, Wenbin Zhang
cs.SEcs.AIcs.LGarXiv:2609.37315v12026
dalex: Responsible Machine Learning with Interactive Explainability and Fairness in Python
Hubert Baniecki, Wojciech Kretowicz, Piotr Piatyszek +2
cs.LGcs.HCcs.SEarXiv:2012.14406v22020
Cross-Domain Evaluation of Transformer-Based Vulnerability Detection on Open & Industry Data
Moritz Mock, Thomas Forrer, Barbara Russo
cs.SEarXiv:2509.09313v12025
From Hugging Face to GitHub: Tracing License Drift in the Open-Source AI Ecosystem
James Jewitt, Hao Li, Bram Adams +2
cs.SEcs.AIarXiv:2509.09873v22025
Developer-LLM Conversations: An Empirical Study of Interactions and Generated Code Quality
Suzhen Zhong, Ying Zou, Bram Adams
cs.SEarXiv:2509.10402v22025
Computational Thinking Reasoning in Large Language Models
Kechi Zhang, Ge Li, Jia Li +9
cs.SEarXiv:2506.02658v22025
GUARD:Dual-Agent based Backdoor Defense on Chain-of-Thought in Neural Code Generation
Naizhu Jin, Zhong Li, Tian Zhang +1
cs.SEarXiv:2505.21425v32025
Code4MeV2: a Research-oriented Code-completion Platform
Roham Koohestani, Parham Bateni, Aydin Ebrahimi +3
cs.SEcs.AIarXiv:2510.03755v12025
Inforence: Effective Fault Localization Based on Information-Theoretic Analysis and Statistical Causal Inference
Farid Feyzi, Saeed Parsa
cs.SEarXiv:1712.03361v12017
The Impact of GenAI on the Future of Requirements Engineering
Travis Breaux, Anmol Singhal
cs.SEarXiv:2609.05667v12026
ASAD: Adaptive Software Agents for Debugging
Yacine Majdoub, Eya Ben Charrada, Haifa Touati
cs.SEarXiv:2610.00629v12026
Spectrum-based Software Fault Localization: A Survey of Techniques, Advances, and Challenges
Higor A. de Souza, Marcos L. Chaim, Fabio Kon
cs.SEarXiv:1607.04347v22016
HyperAgent: Generalist Software Engineering Agents to Solve Coding Tasks at Scale
Huy Nhat Phan, Tien N. Nguyen, Phong X. Nguyen +1
cs.SEcs.AIarXiv:2409.16299v32024
A-JIT: Agentic Just-In-Time Software Construction
Mark Marron, Earl T. Barr
cs.SEcs.AIarXiv:2609.10248v12026
Large Language Models and Language Server Protocol: a match made in context
Alessandro Schena, Ilgiz Mustafin, Julia Kotovich
cs.SEarXiv:2609.03086v12026
MigrationMiner: An Automated Detection Tool of Third-Party Java Library Migration at the Method Level
Hussein Alrubaye, Mohamed Wiem Mkaouer, Ali Ouni
cs.SEcs.CLarXiv:1907.02997v22019
No One Left Behind: Cross-Level Analysis for Sustainable Software Engineering
Masoum Salehi, Sandro Schulze, Jacob Krüger
cs.SEarXiv:2609.03861v12026
Two Truths and A Lie? Benchmarking Off-the-Shelf LLMs for Requirements Quality Assessment: Performance, False Alarms, and Misses
Jannatul Shefa, Alejandro Salado, Paul Wach +1
cs.SEarXiv:2609.03230v12026
Fine-Tuning and Prompt Engineering for Large Language Models-based Code Review Automation
Chanathip Pornprasit, Chakkrit Tantithamthavorn
cs.SEarXiv:2402.00905v42024
AI-powered Code Review with LLMs: Early Results
Zeeshan Rasheed, Malik Abdul Sami, Muhammad Waseem +5
cs.SEarXiv:2404.18496v12024
A GPT-based Code Review System for Programming Language Learning
Lee Dong-Kyu
cs.SEcs.AIarXiv:2407.04722v12024
FinRobot: Generative Business Process AI Agents for Enterprise Resource Planning in Finance
Hongyang Yang, Likun Lin, Yang She +5
cs.AIcs.SEq-fin.GNarXiv:2506.01423v12025
TDAD: Test-Driven Agentic Development - Reducing Code Regressions in AI Coding Agents via Graph-Based Impact Analysis
Pepe Alonso, Sergio Yovine, Victor A. Braberman
cs.SEcs.AIarXiv:2603.17973v22026
CompProv Produces Machine Readable Graphs Encoding Microscopic Algebraic Provenance for Reproducible Computation
Minas Abramyan, Mohammed Alaa Ala'anzy, Nasir Saeed
cs.SEcs.CEarXiv:2610.01203v12026
Towards Trustworthy LLMs for Code: A Data-Centric Synergistic Auditing Framework
Chong Wang, Zhenpeng Chen, Tianlin Li +2
cs.SEarXiv:2410.09048v22024
Software Project Management with LLM-Based Automation: Coordination, Validation, and Governance in Practice
Ronnie de Souza Santos, Cleyton Magalhaes, Italo Santos
cs.SEarXiv:2610.00027v12026
WebCode2M: A Real-World Dataset for Code Generation from Webpage Designs
Yi Gui, Zhen Li, Yao Wan +10
cs.CVcs.AIcs.SEarXiv:2404.06369v22024
Hot or Cold? Adaptive Temperature Sampling for Code Generation with Large Language Models
Yuqi Zhu, Jia Li, Ge Li +4
cs.SEcs.CLarXiv:2309.02772v32023
Reviewer Capability Governs Rejection Targeting, Not Repair Skill: Evidence from LLM Execute-Review-Revise Pipelines
Faizan Tanveer
cs.SEcs.CLcs.MAarXiv:2609.04270v12026
Retrieve and Refine: Exemplar-based Neural Comment Generation
Bolin Wei
cs.SEarXiv:1910.10419v12019
Trustworthy Data- and ML-Ops for Intelligent Transportation Systems and Logistics
Antonio Emanuele Cinà, Giovanni Scodeller, Cecilia Caterina Pasquale +5
cs.AIcs.SEarXiv:2610.01282v12026
Are Large Language Models Memorizing Bug Benchmarks?
Daniel Ramos, Claudia Mamede, Kush Jain +3
cs.SEcs.AIcs.LGarXiv:2411.13323v32024
Benchmarking Energy Efficiency of Large Language Models Using vLLM
K. Pronk, Q. Zhao
cs.SEcs.AIarXiv:2509.08867v12025
The Import Tax: A Longitudinal Measurement of Startup Cost in the Python Ecosystem
Trinath Sai Subhash Reddy Pittala
cs.SEarXiv:2609.02753v12026
SWE-IF: Aligning Code Evaluation with Human Preference
Ming Zhong, Xiang Zhou, Ting-Yun Chang +9
cs.CLcs.AIcs.LGarXiv:2510.07315v22025
Cognitive Biases in Software Engineering: A Systematic Mapping Study
Rahul Mohanani, Iflaah Salman, Burak Turhan +2
cs.SEarXiv:1707.03869v32017
CUA-SWE: When Computer-Use Agents Meet Visual Software Engineering
Prince Zizhuang Wang, Chenhao Liang, Zelong Xu +6
cs.AIcs.SEarXiv:2609.32600v12026
Leveraging Game-Based Platform to Teach Code Refactoring: An Experience with Refactoria
Eman Abdullah AlOmar, Christopher Engelbart, Stephen Pachucki +2
cs.SEarXiv:2609.40086v12026
COMPASS: Predicting the Relationship of Multiple Patches for Vulnerabilities with LLMs
Yi Song, Dongchen Xie, Xiaoyuan Xie +4
cs.SEarXiv:2609.39783v12026
From Verification Failures to Reusable Guidance for Coding Agents
Yuqing Zhai, Xiaohong Chen, Lingming Zhang +2
cs.SEcs.AIcs.LOarXiv:2609.39022v12026
A Multi-Expert Large Language Model Architecture for Verilog Code Generation
Bardia Nadimi, Hao Zheng
cs.LGcs.AIcs.PLarXiv:2404.08029v12024
WebSuite: Systematically Evaluating Why Web Agents Fail
Eric Li, Jim Waldo
cs.SEcs.AIarXiv:2406.01623v12024
Focused-DPO: Enhancing Code Generation Through Focused Preference Optimization on Error-Prone Points
Kechi Zhang, Ge Li, Jia Li +3
cs.SEarXiv:2502.11475v22025
Issue-Oriented Agent-Based Framework for Automated Review Comment Generation
Shuochuan Li, Dong Wang, Patanamon Thongtanunam +3
cs.SEarXiv:2511.00517v12025
Architecting Conversational Data Systems for Stateless LLM APIs: The Hydration Proxy Pattern
Joseph Axisa
cs.AIcs.SEarXiv:2609.01834v12026
WitnessGym: Benchmarking Coding Agents on the Construction of Bug Witnesses
Haomin Qi, Xiangzhe Xu, Yiming Huang +2
cs.SEcs.AIarXiv:2609.36635v12026
CodeCoT: Tackling Code Syntax Errors in CoT Reasoning for Code Generation
Dong Huang, Qingwen Bu, Yuhao Qing +1
cs.SEcs.AIarXiv:2308.08784v22023
Prompt Injection attack against LLM-integrated Applications
Yi Liu, Gelei Deng, Yuekang Li +9
cs.CRcs.AIcs.CLarXiv:2306.05499v32023
Demystifying Agent Skills for Smart Contract Auditing: Design, Effectiveness, Behavioral Impact
Cuifeng Gao, Juantao Zhong, Jiachi Chen +2
cs.SEarXiv:2609.29454v12026
Enhancing repository-level software repair via repository-aware knowledge graphs
Boyang Yang, Jiadong Ren, Shunfu Jin +4
cs.SEarXiv:2503.21710v32025
Mass-Producing Failures of Multimodal Systems with Language Models
Shengbang Tong, Erik Jones, Jacob Steinhardt
cs.LGcs.CLcs.SEarXiv:2306.12105v22023
ControlScope: Workflow Revision and Reliability in LLM Agents
Jingjie Ning, Xueqi Li, Yibo Kong +1
cs.AIcs.CLcs.SEarXiv:2609.34313v12026
A New Skill Based Robot Programming Language Using UML/P Statecharts
Ulrike Thomas, Gerd Hirzinger, Bernhard Rumpe +2
cs.SEcs.ROarXiv:1409.6601v12014
DSpec2Test: Specification-Driven Test Generation in Dafny
Sofia Vieira Pinto, Álvaro F. Silva, João Pascoal Faria +1
cs.SEarXiv:2609.29713v12026
Can MCP Clients Decide What to Do After Failure? A Result-Only Actionability Audit
Rishabh Mehan
cs.SEarXiv:2609.00072v12026
Relic: From Multi-Agent Collaboration to Persistent Organizational Capability
Hongyi Du, Tianyi Zhang, Weijia Zhang +9
cs.AIcs.SEarXiv:2609.32965v12026
Evaluating Code Recommender Systems: A Review
Daniel Borst, Stefan Sobernig
cs.SEarXiv:2609.30351v12026
Conversational Automated Program Repair
Chunqiu Steven Xia, Lingming Zhang
cs.SEcs.LGarXiv:2301.13246v12023

Software Engineering

Towards an AI Software Factory for Data Systems

SafeLLM4SE: Statistical Evaluation and Reporting for LLM-based Software Engineering Systems

Do Agent Benchmarks Do What They Say? An Executable-Contract Audit of Tool-Using Agent Environments

dalex: Responsible Machine Learning with Interactive Explainability and Fairness in Python

Cross-Domain Evaluation of Transformer-Based Vulnerability Detection on Open & Industry Data

From Hugging Face to GitHub: Tracing License Drift in the Open-Source AI Ecosystem

Developer-LLM Conversations: An Empirical Study of Interactions and Generated Code Quality

Computational Thinking Reasoning in Large Language Models

GUARD:Dual-Agent based Backdoor Defense on Chain-of-Thought in Neural Code Generation

Code4MeV2: a Research-oriented Code-completion Platform

Inforence: Effective Fault Localization Based on Information-Theoretic Analysis and Statistical Causal Inference

The Impact of GenAI on the Future of Requirements Engineering

ASAD: Adaptive Software Agents for Debugging

Spectrum-based Software Fault Localization: A Survey of Techniques, Advances, and Challenges

HyperAgent: Generalist Software Engineering Agents to Solve Coding Tasks at Scale

A-JIT: Agentic Just-In-Time Software Construction

Large Language Models and Language Server Protocol: a match made in context

MigrationMiner: An Automated Detection Tool of Third-Party Java Library Migration at the Method Level

No One Left Behind: Cross-Level Analysis for Sustainable Software Engineering

Two Truths and A Lie? Benchmarking Off-the-Shelf LLMs for Requirements Quality Assessment: Performance, False Alarms, and Misses

Fine-Tuning and Prompt Engineering for Large Language Models-based Code Review Automation

AI-powered Code Review with LLMs: Early Results

A GPT-based Code Review System for Programming Language Learning

FinRobot: Generative Business Process AI Agents for Enterprise Resource Planning in Finance

TDAD: Test-Driven Agentic Development - Reducing Code Regressions in AI Coding Agents via Graph-Based Impact Analysis

CompProv Produces Machine Readable Graphs Encoding Microscopic Algebraic Provenance for Reproducible Computation

Towards Trustworthy LLMs for Code: A Data-Centric Synergistic Auditing Framework

Software Project Management with LLM-Based Automation: Coordination, Validation, and Governance in Practice

WebCode2M: A Real-World Dataset for Code Generation from Webpage Designs

Hot or Cold? Adaptive Temperature Sampling for Code Generation with Large Language Models

Reviewer Capability Governs Rejection Targeting, Not Repair Skill: Evidence from LLM Execute-Review-Revise Pipelines

Retrieve and Refine: Exemplar-based Neural Comment Generation

Trustworthy Data- and ML-Ops for Intelligent Transportation Systems and Logistics

Are Large Language Models Memorizing Bug Benchmarks?

Benchmarking Energy Efficiency of Large Language Models Using vLLM

The Import Tax: A Longitudinal Measurement of Startup Cost in the Python Ecosystem

SWE-IF: Aligning Code Evaluation with Human Preference

Cognitive Biases in Software Engineering: A Systematic Mapping Study

CUA-SWE: When Computer-Use Agents Meet Visual Software Engineering

Leveraging Game-Based Platform to Teach Code Refactoring: An Experience with Refactoria

COMPASS: Predicting the Relationship of Multiple Patches for Vulnerabilities with LLMs

From Verification Failures to Reusable Guidance for Coding Agents

A Multi-Expert Large Language Model Architecture for Verilog Code Generation

WebSuite: Systematically Evaluating Why Web Agents Fail

Focused-DPO: Enhancing Code Generation Through Focused Preference Optimization on Error-Prone Points

Issue-Oriented Agent-Based Framework for Automated Review Comment Generation

Architecting Conversational Data Systems for Stateless LLM APIs: The Hydration Proxy Pattern

WitnessGym: Benchmarking Coding Agents on the Construction of Bug Witnesses

CodeCoT: Tackling Code Syntax Errors in CoT Reasoning for Code Generation

Prompt Injection attack against LLM-integrated Applications

Demystifying Agent Skills for Smart Contract Auditing: Design, Effectiveness, Behavioral Impact

Enhancing repository-level software repair via repository-aware knowledge graphs

Mass-Producing Failures of Multimodal Systems with Language Models

ControlScope: Workflow Revision and Reliability in LLM Agents

A New Skill Based Robot Programming Language Using UML/P Statecharts

DSpec2Test: Specification-Driven Test Generation in Dafny

Can MCP Clients Decide What to Do After Failure? A Result-Only Actionability Audit

Relic: From Multi-Agent Collaboration to Persistent Organizational Capability

Evaluating Code Recommender Systems: A Review

Conversational Automated Program Repair