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)

1,741 to 1,800 of 2,784

SWE-ABS: Adversarial Benchmark Strengthening Exposes Inflated Success Rates on Test-based Benchmark
Boxi Yu, Yang Cao, Yuzhong Zhang +9
cs.SEarXiv:2603.00520v12026
Stress Testing Control Loops in Cyber-Physical Systems
Claudio Mandrioli, Seung Yeob Shin, Martina Maggio +2
cs.SEarXiv:2302.13913v42023
SWE-Bench ProMax: Benchmarking Agents on Large-Scale Multilingual Code Refactoring
Yuling Shi, Jinghan Xu, Kelin Fu +12
cs.CLcs.SEarXiv:2608.09802v12026
Extending LLM-based support for software engineers with ADHD
Aarsh Shah, Ronnie de Souza Santos, Italo Santos +2
cs.SEarXiv:2610.00555v12026
SWE-Marathon: Can Agents Autonomously Complete Ultra-Long-Horizon Software Work?
Rishi Desai, Jesse Hu, Joan Cabezas +23
cs.SEcs.AIarXiv:2606.07682v12026
OpenRath: Session-Centered Runtime State for Agent Systems
Fukang Wen, Zhijie Wang, Ruilin Xu
cs.SEcs.PLarXiv:2606.19409v12026
Large Language Models are Zero-Shot Fuzzers: Fuzzing Deep-Learning Libraries via Large Language Models
Yinlin Deng, Chunqiu Steven Xia, Haoran Peng +2
cs.SEarXiv:2212.14834v42022
Nopol: Automatic Repair of Conditional Statement Bugs in Java Programs
Jifeng Xuan, Matias Martinez, Favio Demarco +5
cs.SEarXiv:1811.04211v12018
Modelstamp: Pre-Deserialization Verification of Machine-Learning Artifacts and Runtime Environment State
Anagha Dhekne
cs.SEcs.CRarXiv:2609.01781v12026
Right-Sizing LLM-Agent Decomposition in VAT Determination: A Pilot Controlled Sweep
Pedro Santos
cs.MAcs.AIcs.SEarXiv:2608.23395v12026
BuildBench: Benchmarking LLM Agents on Compiling Real-World Open-Source Software
Zehua Zhang, Ati Priya Bajaj, Divij Handa +14
cs.SEcs.AIcs.PLarXiv:2509.25248v22025
Socratic-SWE: Self-Evolving Coding Agents via Trace-Derived Agent Skills
Chuan Xiao, Zhengbo Jiao, Shaobo Wang +5
cs.SEcs.AIarXiv:2606.07412v12026
Rules to Tools: Executable Checks for LLM Agents in Scientific Computing
Jingjie Ning, Guojiang Zhao, Chen Xu +4
cs.AIcs.SEarXiv:2610.00313v12026
Causal Discovery in the Era of Agents
Yujia Zheng, Vishal Verma, Mantej Gill +3
cs.AIcs.LGcs.SEarXiv:2606.23608v12026
KG-Commit: A Dynamic Knowledge Graph for Online Just-in-Time Software Defect Prediction
Mohsen Hesamolhokama, Mohammad Sina Beyrami Aghbash, Behnam Rohani +2
cs.SEarXiv:2609.06272v22026
Characterizing and Codifying Malware Sophistication
Angelo Porcella, Zachary Wadhams, Clemente Izurieta +2
cs.CRcs.SEarXiv:2610.00098v12026
Docling Technical Report
Christoph Auer, Maksym Lysak, Ahmed Nassar +16
cs.CLcs.CVcs.SEarXiv:2408.09869v52024
Natural Language to Code Translation with Execution
Freda Shi, Daniel Fried, Marjan Ghazvininejad +2
cs.CLcs.SEarXiv:2204.11454v22022
Using Small Language Models to Reverse-Engineer Machine Learning Pipelines Structures
Nicolas Lacroix, Frederic Precioso, Mireille Blay-Fornarino +1
cs.SEcs.LGarXiv:2610.10261v12026
Repository-Level Prompt Generation for Large Language Models of Code
Disha Shrivastava, Hugo Larochelle, Daniel Tarlow
cs.LGcs.AIcs.PLarXiv:2206.12839v32022
Context operations to architecture modelling output from large language models and evaluation criteria for their use in systems engineering design
Vinicius Kaster Marini, Petter Krus
eess.SYcs.AIcs.SEarXiv:2609.10132v12026
Managing Procedural Memory in LLM Agents: Control, Adaptation, and Evaluation
Julia Belikova, Rauf Parchiev, Evgeny Egorov +4
cs.AIcs.CLcs.SEarXiv:2606.23127v12026
Software development in startup companies: A systematic mapping study
Nicolò Paternoster, Carmine Giardino, Michael Unterkalmsteiner +2
cs.SEarXiv:2307.13104v12023
SkillSpec: Intent-Masked Specification Reasoning for Agent Skill Correctness
Yizhuo Zhang, Bo Kang, Yi Yang +3
cs.SEcs.AIarXiv:2609.06052v12026
TritonRL: Training LLMs to Think and Code Triton Without Cheating
Jiin Woo, Shaowei Zhu, Allen Nie +3
cs.SEcs.LGarXiv:2510.17891v22025
SpecCoder: Specification-Aware Code Generation with Curriculum Dual-Task Reinforcement Learning
Yixuan Li, Mingxuan Huang, Jiajing Wang +4
cs.SEarXiv:2609.06041v12026
Nuances are the Key: Unlocking ChatGPT to Find Failure-Inducing Tests with Differential Prompting
Tsz-On Li, Wenxi Zong, Yibo Wang +4
cs.SEarXiv:2304.11686v62023
Evaluating AIGC Detectors on Code Content
Jian Wang, Shangqing Liu, Xiaofei Xie +1
cs.SEarXiv:2304.05193v12023
Code2LoRA: Hypernetwork-Generated Adapters for Code Language Models under Software Evolution
Liliana Hotsko, Yinxi Li, Yuntian Deng +1
cs.SEcs.AIcs.CLarXiv:2606.06492v12026
Challenges and solutions when adopting DevSecOps: A systematic review
Roshan N. Rajapakse, Mansooreh Zahedi, M. Ali Babar +1
cs.SEarXiv:2103.08266v22021
SafeGround: Know When to Trust GUI Grounding Models via Uncertainty Calibration
Qingni Wang, Yue Fan, Xin Eric Wang
cs.AIcs.SEarXiv:2602.02419v22026
Compositional Falsification of Cyber-Physical Systems with Machine Learning Components
Tommaso Dreossi, Alexandre Donzé, Sanjit A. Seshia
eess.SYcs.LGcs.SEarXiv:1703.00978v32017
Decentralised LTL Monitoring
Andreas Bauer, Yliès Falcone
cs.SEarXiv:1111.5133v32011
On the Reliability of LLM-Based Vulnerability Patching Benchmarks
Dang K Le, Wenxuan Shi, Xinyu Xing
cs.CRcs.SEarXiv:2610.10150v12026
Teaching Code LLMs to Use Autocompletion Tools in Repository-Level Code Generation
Chong Wang, Jian Zhang, Yebo Feng +4
cs.SEarXiv:2401.06391v32024
Better Understanding, Better Fixes? A Study of Hallucination in LLM-based Automated Program Repair
Xuemeng Cai, Jiakun Liu, Linhan Yang +2
cs.SEcs.AIarXiv:2609.04909v12026
Regret Dominates Surprise: Design-Time Requirements Engineering for Agentic-AI Safety
Nuwayyir Almohammadi, Rami Bahsoon, Tao Chen
cs.SEarXiv:2609.05692v12026
Who Maintains Agent Skills? A Longitudinal Study of Human-Governed, AI-Assisted Skill Maintenance
Chen Shen, Estevam Hruschka
cs.CLcs.AIcs.HCarXiv:2609.05677v12026
On the Reliability and Explainability of Language Models for Program Generation
Yue Liu, Chakkrit Tantithamthavorn, Yonghui Liu +1
cs.SEarXiv:2302.09587v32023
JTA: Joint Testability Architecture for Scenario-Based Validation of Safety-Critical Software
Wenyao Xue, Jiandi Wang, Yichen Wang
cs.SEcs.ROarXiv:2608.05594v12026
Summaries:简体中文
Look Before You Prompt, and After: Scaffolding Human-AI Collaboration in Software Tutorial Creation
Avinash Bhat, Vy Bui, Jin L. C. Guo
cs.SEcs.HCarXiv:2609.05563v12026
Matching Matters: A Fair Quality-Efficiency Benchmark for Command-Line Agents
Han Chi, Jiaxin Qi, Yan Cui +2
cs.SEcs.AIarXiv:2606.21140v22026
Aletheia: Permission-Minimality Testing for Coding-Agent Rules
Jieke Shi, Yuchen Chen, Junda He +2
cs.CRcs.SEarXiv:2609.39678v12026
Memory as Infrastructure: Reliability Engineering for Persistent Agent Memory in Months-Long LLM-Assisted Development
Mike Helwig
cs.SEarXiv:2609.05510v12026
Self-Edit: Fault-Aware Code Editor for Code Generation
Kechi Zhang, Zhuo Li, Jia Li +2
cs.SEcs.CLarXiv:2305.04087v52023
A Syntactic Neural Model for General-Purpose Code Generation
Pengcheng Yin, Graham Neubig
cs.CLcs.PLcs.SEarXiv:1704.01696v12017
Structured Neural Summarization
Patrick Fernandes, Miltiadis Allamanis, Marc Brockschmidt
cs.LGcs.CLcs.SEarXiv:1811.01824v42018
Comprehension Audits to Mitigate Risks from Automated AI Research
Ronald J. Bodkin, Bahrad A. Sokhansanj, Gillian K. Hadfield
cs.CYcs.AIcs.SEarXiv:2610.10064v12026
AICD Bench: A Challenging Benchmark for AI-Generated Code Detection
Daniil Orel, Dilshod Azizov, Indraneil Paul +3
cs.LGcs.SEarXiv:2602.02079v12026
Large Language Models Meet NL2Code: A Survey
Daoguang Zan, Bei Chen, Fengji Zhang +5
cs.SEcs.AIcs.CLarXiv:2212.09420v22022
BigCodeArena: Unveiling More Reliable Human Preferences in Code Generation via Execution
Terry Yue Zhuo, Xiaolong Jin, Hange Liu +37
cs.SEcs.AIcs.CLarXiv:2510.08697v22025
CodePAD: Sequence-based Code Generation with Pushdown Automaton
Yihong Dong, Xue Jiang, Yuchen Liu +2
cs.SEcs.AIarXiv:2211.00818v42022
EngramBench: A Capability-Grounded Benchmark for Skill-Evolution Harnesses
Zhixuan Tan, Pengjie Gu, Zhao Li +4
cs.SEcs.AIarXiv:2609.39284v12026
A Comprehensive Survey on Fog Computing: State-of-the-art and Research Challenges
Carla Mouradian, Diala Naboulsi, Sami Yangui +3
cs.DCcs.SEarXiv:1710.11001v32017
VeriGuard: Enhancing LLM Agent Safety via Verified Code Generation
Lesly Miculicich, Mihir Parmar, Hamid Palangi +4
cs.SEcs.AIcs.CRarXiv:2510.05156v12025
Quantisation of Abstract Data Types
Mingsheng Ying, Zhicheng Zhang, Kean Chen
quant-phcs.PLcs.SEarXiv:2609.03778v12026
Antipatterns in AI-assisted Qualitative Data Analysis: A Catalog of Temptations and Pitfalls for Software Engineering Researchers
Rashina Hoda, Carolyn Seaman, Victoria Gomes +1
cs.SEcs.AIarXiv:2608.27927v12026
Model-Based Retargeting to Many-Core CPS: Simulink-to-OpenCL Workflow
Ryuga Chiba, Hiroshi Fujimoto, Takuya Azumi
cs.SEarXiv:2609.29311v12026
Cross-Benchmark Transfer from RL on Agentic Coding Tasks
Sushant Mehta, Logan Ritchie, Edwin Chen
cs.LGcs.AIcs.SEarXiv:2610.00890v12026
How Effective Are Neural Networks for Fixing Security Vulnerabilities
Yi Wu, Nan Jiang, Hung Viet Pham +5
cs.SEcs.AIcs.CRarXiv:2305.18607v22023

Software Engineering

SWE-ABS: Adversarial Benchmark Strengthening Exposes Inflated Success Rates on Test-based Benchmark

Stress Testing Control Loops in Cyber-Physical Systems

SWE-Bench ProMax: Benchmarking Agents on Large-Scale Multilingual Code Refactoring

Extending LLM-based support for software engineers with ADHD

SWE-Marathon: Can Agents Autonomously Complete Ultra-Long-Horizon Software Work?

OpenRath: Session-Centered Runtime State for Agent Systems

Large Language Models are Zero-Shot Fuzzers: Fuzzing Deep-Learning Libraries via Large Language Models

Nopol: Automatic Repair of Conditional Statement Bugs in Java Programs

Modelstamp: Pre-Deserialization Verification of Machine-Learning Artifacts and Runtime Environment State

Right-Sizing LLM-Agent Decomposition in VAT Determination: A Pilot Controlled Sweep

BuildBench: Benchmarking LLM Agents on Compiling Real-World Open-Source Software

Socratic-SWE: Self-Evolving Coding Agents via Trace-Derived Agent Skills

Rules to Tools: Executable Checks for LLM Agents in Scientific Computing

Causal Discovery in the Era of Agents

KG-Commit: A Dynamic Knowledge Graph for Online Just-in-Time Software Defect Prediction

Characterizing and Codifying Malware Sophistication

Docling Technical Report

Natural Language to Code Translation with Execution

Using Small Language Models to Reverse-Engineer Machine Learning Pipelines Structures

Repository-Level Prompt Generation for Large Language Models of Code

Context operations to architecture modelling output from large language models and evaluation criteria for their use in systems engineering design

Managing Procedural Memory in LLM Agents: Control, Adaptation, and Evaluation

Software development in startup companies: A systematic mapping study

SkillSpec: Intent-Masked Specification Reasoning for Agent Skill Correctness

TritonRL: Training LLMs to Think and Code Triton Without Cheating

SpecCoder: Specification-Aware Code Generation with Curriculum Dual-Task Reinforcement Learning

Nuances are the Key: Unlocking ChatGPT to Find Failure-Inducing Tests with Differential Prompting

Evaluating AIGC Detectors on Code Content

Code2LoRA: Hypernetwork-Generated Adapters for Code Language Models under Software Evolution

Challenges and solutions when adopting DevSecOps: A systematic review

SafeGround: Know When to Trust GUI Grounding Models via Uncertainty Calibration

Compositional Falsification of Cyber-Physical Systems with Machine Learning Components

Decentralised LTL Monitoring

On the Reliability of LLM-Based Vulnerability Patching Benchmarks

Teaching Code LLMs to Use Autocompletion Tools in Repository-Level Code Generation

Better Understanding, Better Fixes? A Study of Hallucination in LLM-based Automated Program Repair

Regret Dominates Surprise: Design-Time Requirements Engineering for Agentic-AI Safety

Who Maintains Agent Skills? A Longitudinal Study of Human-Governed, AI-Assisted Skill Maintenance

On the Reliability and Explainability of Language Models for Program Generation

JTA: Joint Testability Architecture for Scenario-Based Validation of Safety-Critical Software

Look Before You Prompt, and After: Scaffolding Human-AI Collaboration in Software Tutorial Creation

Matching Matters: A Fair Quality-Efficiency Benchmark for Command-Line Agents

Aletheia: Permission-Minimality Testing for Coding-Agent Rules

Memory as Infrastructure: Reliability Engineering for Persistent Agent Memory in Months-Long LLM-Assisted Development

Self-Edit: Fault-Aware Code Editor for Code Generation

A Syntactic Neural Model for General-Purpose Code Generation

Structured Neural Summarization

Comprehension Audits to Mitigate Risks from Automated AI Research

AICD Bench: A Challenging Benchmark for AI-Generated Code Detection

Large Language Models Meet NL2Code: A Survey

BigCodeArena: Unveiling More Reliable Human Preferences in Code Generation via Execution

CodePAD: Sequence-based Code Generation with Pushdown Automaton

EngramBench: A Capability-Grounded Benchmark for Skill-Evolution Harnesses

A Comprehensive Survey on Fog Computing: State-of-the-art and Research Challenges

VeriGuard: Enhancing LLM Agent Safety via Verified Code Generation

Quantisation of Abstract Data Types

Antipatterns in AI-assisted Qualitative Data Analysis: A Catalog of Temptations and Pitfalls for Software Engineering Researchers

Model-Based Retargeting to Many-Core CPS: Simulink-to-OpenCL Workflow

Cross-Benchmark Transfer from RL on Agentic Coding Tasks

How Effective Are Neural Networks for Fixing Security Vulnerabilities