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)

481 to 540 of 1,389

SkillReducer: Optimizing LLM Agent Skills for Token Efficiency
Yudong Gao, Zongjie Li, Yuanyuan Yuan +3
cs.SEarXiv:2603.29919v22026
An Analysis of the Search Spaces for Generate and Validate Patch Generation Systems
Fan Long, Martin Rinard
cs.SEarXiv:1602.05643v12016
Harness Engineering in LLM Tool Use via Agent-Native Reusable Tool Primitives
Haibo Jin, Suijin Wang, Xucheng Yu +2
cs.SEcs.AIcs.CLarXiv:2609.01736v12026
Understanding Software Engineering Agents: A Study of Thought-Action-Result Trajectories
Islem Bouzenia, Michael Pradel
cs.SEcs.AIarXiv:2506.18824v22025
RepoAudit: An Autonomous LLM-Agent for Repository-Level Code Auditing
Jinyao Guo, Chengpeng Wang, Xiangzhe Xu +2
cs.SEcs.PLarXiv:2501.18160v32025
StarCoder: may the source be with you!
Raymond Li, Loubna Ben Allal, Yangtian Zi +64
cs.CLcs.AIcs.PLarXiv:2305.06161v22023
SWE-Milestone: Evaluating AI Agents on Continuous Software Evolution
Gangda Deng, Zhaoling Chen, Zhongming Yu +11
cs.SEcs.AIarXiv:2603.13428v42026
Conformance Checking Based on Multi-Perspective Declarative Process Models
Andrea Burattin, Fabrizio Maria Maggi, Alessandro Sperduti
cs.SEcs.DBcs.LOarXiv:1503.04957v12015
SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software Engineering?
Samuel Miserendino, Michele Wang, Tejal Patwardhan +1
cs.LGcs.SEarXiv:2502.12115v42025
Agentic Software Engineering: Foundational Pillars and a Research Roadmap
Ahmed E. Hassan, Hao Li, Dayi Lin +4
cs.SEcs.AIarXiv:2509.06216v32025
Multi-Modal Attention Network Learning for Semantic Source Code Retrieval
Yao Wan, Jingdong Shu, Yulei Sui +4
cs.SEcs.PLarXiv:1909.13516v12019
CATERPILLAR: A Business Process Execution Engine on the Ethereum Blockchain
Orlenys López-Pintado, Luciano García-Bañuelos, Marlon Dumas +2
cs.SEarXiv:1808.03517v32018
Vibe Coding in Practice: Motivations, Challenges, and a Future Outlook -- a Grey Literature Review
Ahmed Fawzy, Amjed Tahir, Kelly Blincoe
cs.SEarXiv:2510.00328v12025
Framework and Benchmark for Code-Driven Agentic Testing in Web Development
Bin Hong, Zhenchao Zhang, Jiyuan He +2
cs.SEarXiv:2609.00081v12026
Beneath the Diff: Diagnosing and Mitigating Algorithmic Mode Collapse in Code-Level Autonomous Research Loops
Bowei He, Weixu Zhang, Yili Jin +1
cs.CLcs.SEarXiv:2609.00077v12026
Probabilistic Model Checking of Autoregressive Neural Sequence Models
Helge Spieker, Dennis Gross, Arnaud Gotlieb
cs.SEcs.AIarXiv:2609.00838v12026
Schwarz: Solver-Aware Agentic Program Verification
Jingyu Ke, Ling-I Wu, Guoqiang Li
cs.LOcs.SEarXiv:2608.30803v12026
Developer Prioritization in Bug Repositories
Jifeng Xuan, He Jiang, Zhilei Ren +1
cs.SEarXiv:1704.04764v12017
Make LLM a Testing Expert: Bringing Human-like Interaction to Mobile GUI Testing via Functionality-aware Decisions
Zhe Liu, Chunyang Chen, Junjie Wang +5
cs.SEarXiv:2310.15780v12023
WiseSpec: Requirements-Driven Agents for Code Generation
Zhao Tian
cs.SEcs.AIarXiv:2609.00568v12026
Does Fault Localization Beat a Fresh Attempt? A Placebo-Controlled Study of Test-Guided Code Repair
Anik Jha
cs.SEcs.AIcs.LGarXiv:2609.00854v12026
On the Prospects of Dynamic LLM Conversations in Software Development
Annemarie Wittig, Alina Mailach, Janet Siegmund +1
cs.SEcs.AIarXiv:2608.30756v12026
CWEval: Outcome-driven Evaluation on Functionality and Security of LLM Code Generation
Jinjun Peng, Leyi Cui, Kele Huang +2
cs.SEcs.CLcs.LGarXiv:2501.08200v12025
Designing an Auditable LLM-Supported Workflow for Qualitative Thematic Analysis
Nadia Jul Jeldtoft, Tariq Yousef
cs.AIcs.SEarXiv:2608.30543v12026
Towards a Reliable and Practical Eval Pipeline
Emma Thuong Nguyen, Abhishek Ghose
cs.AIcs.SEarXiv:2609.00805v12026
MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue Resolution
Wei Tao, Yucheng Zhou, Yanlin Wang +3
cs.SEcs.AIarXiv:2403.17927v22024
Kevin: Multi-Turn RL for Generating CUDA Kernels
Carlo Baronio, Pietro Marsella, Ben Pan +2
cs.LGcs.AIcs.PFarXiv:2507.11948v12025
Spec-Driven Development for Agentic Software Engineering: Harnessing Human-Agent Teamwork
Jessica Diaz, Joaquin Gayoso, Andrea Cimminio +1
cs.SEarXiv:2609.00252v12026
PentestGPT: An LLM-empowered Automatic Penetration Testing Tool
Gelei Deng, Yi Liu, Víctor Mayoral-Vilches +7
cs.SEcs.CRarXiv:2308.06782v22023
Oreo: Detection of Clones in the Twilight Zone
Vaibhav Saini, Farima Farmahinifarahani, Yadong Lu +2
cs.SEarXiv:1806.05837v12018
Neural Transfer Learning for Repairing Security Vulnerabilities in C Code
Zimin Chen, Steve Kommrusch, Martin Monperrus
cs.SEcs.CRcs.LGarXiv:2104.08308v32021
A Systematic Review of Unsupervised Learning Techniques for Software Defect Prediction
Ning Li, Martin Shepperd, Yuchen Guo
cs.SEarXiv:1907.12027v42019
A Survey on Code Generation with LLM-based Agents
Yihong Dong, Xue Jiang, Jiaru Qian +4
cs.SEcs.AIcs.CLarXiv:2508.00083v22025
Model Context Protocol (MCP) at First Glance: Studying the Security and Maintainability of MCP Servers
Mohammed Mehedi Hasan, Hao Li, Emad Fallahzadeh +3
cs.SEcs.ETarXiv:2506.13538v52025
Software Engineering Challenges of Deep Learning
Anders Arpteg, Björn Brinne, Luka Crnkovic-Friis +1
cs.SEcs.AIcs.LGarXiv:1810.12034v12018
Repository-Level Prompt Generation for Large Language Models of Code
Disha Shrivastava, Hugo Larochelle, Daniel Tarlow
cs.LGcs.AIcs.PLarXiv:2206.12839v32022
On the Use of Agentic Coding: An Empirical Study of Pull Requests on GitHub
Miku Watanabe, Hao Li, Yutaro Kashiwa +3
cs.SEarXiv:2509.14745v32025
Reliable LLM-Generated Programs for High-Energy Physics Experiments through Graph-Grounded Software Knowledge
Yue Sun, Tong Liu, Yipu Liao +2
cs.SEhep-exarXiv:2609.01095v12026
CWM: An Open-Weights LLM for Research on Code Generation with World Models
FAIR CodeGen team, Jade Copet, Quentin Carbonneaux +48
cs.SEcs.AIcs.LGarXiv:2510.02387v12025
Identifying Patch Correctness in Test-Based Program Repair
Yingfei Xiong, Xinyuan Liu, Muhan Zeng +2
cs.SEarXiv:1706.09120v32017
SWE-rebench: An Automated Pipeline for Task Collection and Decontaminated Evaluation of Software Engineering Agents
Ibragim Badertdinov, Alexander Golubev, Maksim Nekrashevich +6
cs.SEcs.CLarXiv:2505.20411v22025
OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents
Thomas Kuntz, Agatha Duzan, Hao Zhao +4
cs.SEcs.LGarXiv:2506.14866v22025
Can LLMs Replace Human Evaluators? An Empirical Study of LLM-as-a-Judge in Software Engineering
Ruiqi Wang, Jiyu Guo, Cuiyun Gao +3
cs.SEcs.AIarXiv:2502.06193v32025
Technology Readiness Levels for AI & ML
Alexander Lavin, Gregory Renard
cs.SEcs.AIcs.LGarXiv:2006.12497v32020
Beyond Locks and Thread IDs: Static Data Race Detection Off The Beaten Path (Extended Version)
Daniel Bund, Julian Erhard, Michael Petter +1
cs.PLcs.SEarXiv:2609.00246v12026
AgOSS: A Dataset and Multi-Layer Characterization of Open-Source Agricultural Software
Vatsal Dudhaiya, Mikhail Golovenchits, Aryan Banerjee +1
cs.SEarXiv:2609.02591v12026
Natural Emergent Misalignment from Reward Hacking in Production RL
Monte MacDiarmid, Benjamin Wright, Jonathan Uesato +19
cs.AIcs.SEarXiv:2511.18397v12025
Engineering Reliable Coding Agents: Evaluating and Operating the System Around the Model
Stephanie Jarmak
cs.SEcs.AIarXiv:2608.13867v12026
Automated Vulnerability Injection in Smart Contracts Using Large Language Models
Luca Migliaccio, Roberto Natella, Naghmeh Ivaki +2
cs.SEcs.AIcs.CRarXiv:2609.02624v12026
Summaries:한국어
POLYFLOW: A Neuro-Symbolic Framework for Static Cross-Language Information Flow Analysis
Haoran Yang, Zhixuan Zhong, Jiawei Guo +1
cs.CRcs.PLcs.SEarXiv:2608.29808v12026
Repair Is Nearly Generation: Multilingual Program Repair with LLMs
Harshit Joshi, José Cambronero, Sumit Gulwani +3
cs.SEcs.AIcs.PLarXiv:2208.11640v32022
Towards an Understanding of Large Language Models in Software Engineering Tasks
Zibin Zheng, Kaiwen Ning, Qingyuan Zhong +5
cs.SEarXiv:2308.11396v32023
ReproAgent: Contract-Guided Paper-to-Code Reproduction
Xue Hu, Zewei Pan, Zhongyuan Wang +3
cs.AIcs.SEarXiv:2608.24291v12026
REVERE: Reflective Evolving Research Engineer
Balaji Dinesh Gangireddi, Aniketh Garikaparthi, Manasi Patwardhan +1
cs.SEcs.AIarXiv:2603.20667v22026
Seeing is Coding: On the Effectiveness of Vision Language Models in Code Understanding
Yuling Shi, Chaoxiang Xie, Zhensu Sun +7
cs.CLcs.SEarXiv:2602.01785v32026
Is Self-Repair a Silver Bullet for Code Generation?
Theo X. Olausson, Jeevana Priya Inala, Chenglong Wang +2
cs.CLcs.AIcs.PLarXiv:2306.09896v52023
The Empire, Long Divided, Must Unite: Architectural Convergence in Three LLM Agent Harnesses
Dai Jiahong
cs.SEcs.AIcs.CEarXiv:2608.23953v12026
DreamBench-SWE: A Multi-Session Memory-Hygiene Benchmark for Software Agents
Sarthak Singh
cs.AIcs.SEarXiv:2608.20664v12026
FlavourBench: Ranking Frontier Language Models with Executable Culinary Ground Truth
Josef Chen, Erim Hayretci
cs.AIcs.CYcs.LGarXiv:2608.20574v12026
Resume Means Resume: A Machine-Checked Conformance Contract for Checkpoint, Interrupt, and Resume Semantics in Workflow Persistence Layers
Sajjad Khan
cs.LGcs.DCcs.LOarXiv:2608.03836v32026

Software Engineering

SkillReducer: Optimizing LLM Agent Skills for Token Efficiency

An Analysis of the Search Spaces for Generate and Validate Patch Generation Systems

Harness Engineering in LLM Tool Use via Agent-Native Reusable Tool Primitives

Understanding Software Engineering Agents: A Study of Thought-Action-Result Trajectories

RepoAudit: An Autonomous LLM-Agent for Repository-Level Code Auditing

StarCoder: may the source be with you!

SWE-Milestone: Evaluating AI Agents on Continuous Software Evolution

Conformance Checking Based on Multi-Perspective Declarative Process Models

SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software Engineering?

Agentic Software Engineering: Foundational Pillars and a Research Roadmap

Multi-Modal Attention Network Learning for Semantic Source Code Retrieval

CATERPILLAR: A Business Process Execution Engine on the Ethereum Blockchain

Vibe Coding in Practice: Motivations, Challenges, and a Future Outlook -- a Grey Literature Review

Framework and Benchmark for Code-Driven Agentic Testing in Web Development

Beneath the Diff: Diagnosing and Mitigating Algorithmic Mode Collapse in Code-Level Autonomous Research Loops

Probabilistic Model Checking of Autoregressive Neural Sequence Models

Schwarz: Solver-Aware Agentic Program Verification

Developer Prioritization in Bug Repositories

Make LLM a Testing Expert: Bringing Human-like Interaction to Mobile GUI Testing via Functionality-aware Decisions

WiseSpec: Requirements-Driven Agents for Code Generation

Does Fault Localization Beat a Fresh Attempt? A Placebo-Controlled Study of Test-Guided Code Repair

On the Prospects of Dynamic LLM Conversations in Software Development

CWEval: Outcome-driven Evaluation on Functionality and Security of LLM Code Generation

Designing an Auditable LLM-Supported Workflow for Qualitative Thematic Analysis

Towards a Reliable and Practical Eval Pipeline

MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue Resolution

Kevin: Multi-Turn RL for Generating CUDA Kernels

Spec-Driven Development for Agentic Software Engineering: Harnessing Human-Agent Teamwork

PentestGPT: An LLM-empowered Automatic Penetration Testing Tool

Oreo: Detection of Clones in the Twilight Zone

Neural Transfer Learning for Repairing Security Vulnerabilities in C Code

A Systematic Review of Unsupervised Learning Techniques for Software Defect Prediction

A Survey on Code Generation with LLM-based Agents

Model Context Protocol (MCP) at First Glance: Studying the Security and Maintainability of MCP Servers

Software Engineering Challenges of Deep Learning

Repository-Level Prompt Generation for Large Language Models of Code

On the Use of Agentic Coding: An Empirical Study of Pull Requests on GitHub

Reliable LLM-Generated Programs for High-Energy Physics Experiments through Graph-Grounded Software Knowledge

CWM: An Open-Weights LLM for Research on Code Generation with World Models

Identifying Patch Correctness in Test-Based Program Repair

SWE-rebench: An Automated Pipeline for Task Collection and Decontaminated Evaluation of Software Engineering Agents

OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents

Can LLMs Replace Human Evaluators? An Empirical Study of LLM-as-a-Judge in Software Engineering

Technology Readiness Levels for AI & ML

Beyond Locks and Thread IDs: Static Data Race Detection Off The Beaten Path (Extended Version)

AgOSS: A Dataset and Multi-Layer Characterization of Open-Source Agricultural Software

Natural Emergent Misalignment from Reward Hacking in Production RL

Engineering Reliable Coding Agents: Evaluating and Operating the System Around the Model

Automated Vulnerability Injection in Smart Contracts Using Large Language Models

POLYFLOW: A Neuro-Symbolic Framework for Static Cross-Language Information Flow Analysis

Repair Is Nearly Generation: Multilingual Program Repair with LLMs

Towards an Understanding of Large Language Models in Software Engineering Tasks

ReproAgent: Contract-Guided Paper-to-Code Reproduction

REVERE: Reflective Evolving Research Engineer

Seeing is Coding: On the Effectiveness of Vision Language Models in Code Understanding

Is Self-Repair a Silver Bullet for Code Generation?

The Empire, Long Divided, Must Unite: Architectural Convergence in Three LLM Agent Harnesses

DreamBench-SWE: A Multi-Session Memory-Hygiene Benchmark for Software Agents

FlavourBench: Ranking Frontier Language Models with Executable Culinary Ground Truth

Resume Means Resume: A Machine-Checked Conformance Contract for Checkpoint, Interrupt, and Resume Semantics in Workflow Persistence Layers