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)

1,561 to 1,620 of 2,780

A Contract-Centered Architecture for Scalable and Manageable Agentic Runtimes
Yaxiao Liu, Pengbo Liu, Yiwen Liu +3
cs.AIcs.MAcs.SEarXiv:2608.27086v12026
SkillOpt-Lite: Better and Faster Agent Self-evolution via One Line of Vibe
Yifei Shen, Bo Li, Xinjie Zhang
cs.SEcs.AIcs.LGarXiv:2607.03451v12026
Synthesizing Proofs Using Proof Sharding and Exploration
Seyed Armin Vakil Ghahani, Manos Kapritsos
cs.PLcs.SEarXiv:2609.28535v12026
Enchanting Program Specification Synthesis by Large Language Models using Static Analysis and Program Verification
Cheng Wen, Jialun Cao, Jie Su +6
cs.SEarXiv:2404.00762v22024
A Mixed-Method Empirical Study of LLM Assistance in Software Engineering Workflows
Pamali D. Weerasinghe, Roshan N. Rajapakse, Isuru Dharmadasa +1
cs.SEarXiv:2609.04214v12026
AgentLogs: A Dataset for Opening the Black Box of GitHub's Cloud Agent
Jonan Richards, Kosei Horikawa, Youmei Fan +2
cs.SEcs.AIarXiv:2608.29204v12026
Harnessing Evolution for Multi-Hunk Program Repair
Seemanta Saha, Ripon K. Saha, Mukul R. Prasad
cs.SEarXiv:1906.08903v12019
Follow Me at the Edge: Mobility-Aware Dynamic Service Placement for Mobile Edge Computing
Tao Ouyang, Zhi Zhou, Xu Chen
cs.NIcs.AIcs.DCarXiv:1809.05239v12018
HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness?
Yuhao Wu, Jingyuan Zhang, Jiajun Shi +16
cs.SEcs.CLarXiv:2609.01437v12026
Large Language Models for Code Analysis: Do LLMs Really Do Their Job?
Chongzhou Fang, Ning Miao, Shaurya Srivastav +8
cs.SEcs.CRarXiv:2310.12357v22023
SWE-Together: Evaluating Coding Agents in Interactive User Sessions
Yifan Wu, Zhuokai Zhao, Songlin Li +8
cs.SEcs.AIarXiv:2606.29957v12026
SWE-Master: Unleashing the Potential of Software Engineering Agents via Post-Training
Huatong Song, Lisheng Huang, Shuang Sun +11
cs.SEcs.CLarXiv:2602.03411v22026
Deep API Learning
Xiaodong Gu, Hongyu Zhang, Dongmei Zhang +1
cs.SEcs.CLcs.LGarXiv:1605.08535v32016
Understanding and Detecting Flaky Builds in GitHub Actions
Wenhao Ge, Chen Zhang
cs.SEarXiv:2602.02307v12026
Is "Better Data" Better than "Better Data Miners"? (On the Benefits of Tuning SMOTE for Defect Prediction)
Amritanshu Agrawal, Tim Menzies
cs.SEarXiv:1705.03697v32017
ProofWright: Towards Agentic Formal Verification of CUDA
Bodhisatwa Chatterjee, Drew Zagieboylo, Sana Damani +2
cs.SEarXiv:2511.12294v22025
CoderUJB: An Executable and Unified Java Benchmark for Practical Programming Scenarios
Zhengran Zeng, Yidong Wang, Rui Xie +2
cs.SEarXiv:2403.19287v12024
Learning from the Test: Self-Referential Differential Testing for Deep RL Agents
Junda He, Jieke Shi, Zhou Yang +2
cs.SEcs.AIcs.LGarXiv:2608.22284v12026
Generalization or Memorization: Data Contamination and Trustworthy Evaluation for Large Language Models
Yihong Dong, Xue Jiang, Huanyu Liu +4
cs.CLcs.AIcs.CRarXiv:2402.15938v32024
Confucius Code Agent: Scalable Agent Scaffolding for Real-World Codebases
Sherman Wong, Zhenting Qi, Zhaodong Wang +8
cs.CLcs.AIcs.LGarXiv:2512.10398v62025
Human oversight of agentic systems in practice: Examining the oversight work, challenges, and heuristics of developers using software agents
Shipi Dhanorkar, Samir Passi, Mihaela Vorvoreanu
cs.SEcs.AIarXiv:2606.05391v12026
Operator Packages, Proposer Strength, and Construction-Family Plateaus in Office-Scale Verified Search
Roberto I. Ono Filho
cs.CLcs.AIcs.LGarXiv:2609.29636v12026
PIPE-Cypher: Automatic Enterprise Benchmark Generation for Text-to-Cypher Systems
Suraj Ranganath, Anish Raghavendra
cs.LGcs.AIcs.DBarXiv:2606.08481v12026
Poison Attack and Defense on Deep Source Code Processing Models
Jia Li, Zhuo Li, Huangzhao Zhang +4
cs.SEcs.AIarXiv:2210.17029v12022
MalSkillBench: A Runtime-Verified Benchmark of Malicious Agent Skills
Wenbo Guo, Wei Zeng, Chengwei Liu +5
cs.CRcs.SEarXiv:2606.07131v32026
DRACO: Fine-Grained Credit Assignment with Dynamic Rubrics for Long-Horizon Agent Training
Shubham Gandhi, Saurabh Goyal, Kiran Kate +1
cs.AIcs.LGcs.SEarXiv:2609.04094v12026
Scenario-Guided LLM-based Mobile App GUI Testing
Shengcheng Yu, Yuchen Ling, Chunrong Fang +5
cs.SEarXiv:2506.05079v42025
Studying the Characteristics of AIOps Projects on GitHub
Roozbeh Aghili, Heng Li, Foutse Khomh
cs.SEarXiv:2212.13245v22022
Investigating Explainability of Generative AI for Code through Scenario-based Design
Jiao Sun, Q. Vera Liao, Michael Muller +4
cs.HCcs.AIcs.SEarXiv:2202.04903v12022
Replications, Revisions, and Reanalyses: Managing Empirical Evidence in Software Engineering
Julian Frattini, Jannik Fischbach, Davide Fucci +4
cs.SEarXiv:2609.05983v12026
ObliVul: Alert-Conditioned Safety Obligation Modeling and Bidirectional Counterfactual Validation for Code Vulnerability Detection
Heyang Tan, Chengxin Gao, Xin Wen +2
cs.SEarXiv:2610.11801v12026
Towards Accountability for Machine Learning Datasets: Practices from Software Engineering and Infrastructure
Ben Hutchinson, Andrew Smart, Alex Hanna +5
cs.LGcs.CYcs.DBarXiv:2010.13561v22020
Verification-Time Dependency on a Disappearing Evaluator
Ho Wa Ku, Jameel Ahmed Siddiqui
cs.CYcs.SEarXiv:2608.29912v12026
Predicting Program Exit Code with LLMs and Programming Language Semantics
Lara Marinov, Aditya Thimmaiah, Jayanth Srinivasa +2
cs.PLcs.AIcs.CLarXiv:2609.00579v12026
GameDevBench: Evaluating Agentic Capabilities Through Game Development
Wayne Chi, Yixiong Fang, Arnav Yayavaram +8
cs.AIcs.CLcs.SEarXiv:2602.11103v22026
UniDebugger: Hierarchical Multi-Agent Framework for Unified Software Debugging
Cheryl Lee, Chunqiu Steven Xia, Longji Yang +4
cs.SEarXiv:2404.17153v32024
Continuous Process-Level Evaluation for Evolving Enterprise AI Agent Skills
Ngoc Phuoc An Vo, Aarya Doshi, Vadim Sheinin
cs.AIcs.SEarXiv:2610.01833v12026
LLM-Enhanced Commit Message Generation via Issue Information: An Exploratory Study
Zongen Ren, Wei Shi, Bo Xiong +2
cs.SEarXiv:2608.22004v12026
StarCoder: may the source be with you!
Raymond Li, Loubna Ben Allal, Yangtian Zi +64
cs.CLcs.AIcs.PLarXiv:2305.06161v22023
WebCoderBench: Benchmarking Web Application Generation with Comprehensive and Interpretable Evaluation Metrics
Chenxu Liu, Yingjie Fu, Wei Yang +2
cs.SEcs.AIarXiv:2601.02430v32026
A Large-Scale Survey on the Usability of AI Programming Assistants: Successes and Challenges
Jenny T. Liang, Chenyang Yang, Brad A. Myers
cs.SEcs.AIcs.HCarXiv:2303.17125v22023
Bugs in Large Language Models Generated Code: An Empirical Study
Florian Tambon, Arghavan Moradi Dakhel, Amin Nikanjam +3
cs.SEcs.AIarXiv:2403.08937v22024
WebCompass: Towards Multimodal Web Coding Evaluation for Code Language Models
Xinping Lei, Xinyu Che, Junqi Xiong +16
cs.SEcs.AIarXiv:2604.18224v12026
PaperFit: Vision-in-the-Loop Typesetting Optimization for Scientific Documents
Bihui Yu, Xinglong Xu, Junjie Jiang +6
cs.AIcs.SEarXiv:2605.10341v12026
Repair Is Nearly Generation: Multilingual Program Repair with LLMs
Harshit Joshi, José Cambronero, Sumit Gulwani +3
cs.SEcs.AIcs.PLarXiv:2208.11640v32022
Kimi-Dev: Agentless Training as Skill Prior for SWE-Agents
Zonghan Yang, Shengjie Wang, Kelin Fu +18
cs.AIcs.CLcs.SEarXiv:2509.23045v32025
Software Engineering for AI-driven Building Operation
Philipp Zech, Sascha Hammes, Johannes Weninger +2
cs.SEcs.AIarXiv:2608.16237v12026
InteractBench: Benchmarking LLMs on Competitive Programming under Unrevealed Information
Jiaze Li, Aocheng Shen, Bing Liu +4
cs.SEcs.AIcs.CLarXiv:2608.29632v12026
A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT
Jules White, Quchen Fu, Sam Hays +6
cs.SEcs.AIarXiv:2302.11382v12023
Teaching an Old LLM Secure Coding: Localized Preference Optimization on Distilled Preferences
Mohammad Saqib Hasan, Saikat Chakraborty, Santu Karmaker +1
cs.CRcs.SEarXiv:2506.00419v22025
UI2App: Benchmarking Visual Interaction Inference in Executable Web Application Generation
Grace Man Chen, Litao Guo, Yifan Wu +5
cs.SEcs.AIcs.CVarXiv:2607.06306v12026
Learning from Mutants: Using Code Mutation to Learn and Monitor Invariants of a Cyber-Physical System
Yuqi Chen, Christopher M. Poskitt, Jun Sun
cs.SEcs.CRcs.LGarXiv:1801.00903v22018
Planning-Driven Programming: A Large Language Model Programming Workflow
Chao Lei, Yanchuan Chang, Nir Lipovetzky +1
cs.SEcs.AIarXiv:2411.14503v32024
A Transformer-based Approach for Source Code Summarization
Wasi Uddin Ahmad, Saikat Chakraborty, Baishakhi Ray +1
cs.SEcs.AIcs.LGarXiv:2005.00653v12020
A Deep Dive into Large Language Models for Automated Bug Localization and Repair
Soneya Binta Hossain, Nan Jiang, Qiang Zhou +5
cs.SEarXiv:2404.11595v32024
Reading Between the Lines: Modeling User Behavior and Costs in AI-Assisted Programming
Hussein Mozannar, Gagan Bansal, Adam Fourney +1
cs.SEcs.HCcs.LGarXiv:2210.14306v52022
kRAIG: A Natural Language-Driven Agent for Automated DataOps Pipeline Generation
Rohan Siva, Kai Cheung, Lichi Li +1
cs.SEcs.AIcs.CLarXiv:2603.20311v12026
Adaptive Strategy Generation for Boundary Value Exploration Beyond Numeric Inputs
Sabinakhon Akbarova, Felix Dobslaw, Robert Feldt
cs.SEarXiv:2608.28230v12026
Learning to Solve and Verify: A Self-Play Framework for Code and Test Generation
Zi Lin, Sheng Shen, Ilia Kulikov +3
cs.SEarXiv:2502.14948v42025
Specification-first convergence with an AI coding agent: a case study of dismantling a core architectural invariant across 189 files in a 717k-line codebase with no test oracle and no human code review
Joel Abenhaim
cs.SEcs.AIarXiv:2608.12440v12026

Software Engineering

A Contract-Centered Architecture for Scalable and Manageable Agentic Runtimes

SkillOpt-Lite: Better and Faster Agent Self-evolution via One Line of Vibe

Synthesizing Proofs Using Proof Sharding and Exploration

Enchanting Program Specification Synthesis by Large Language Models using Static Analysis and Program Verification

A Mixed-Method Empirical Study of LLM Assistance in Software Engineering Workflows

AgentLogs: A Dataset for Opening the Black Box of GitHub's Cloud Agent

Harnessing Evolution for Multi-Hunk Program Repair

Follow Me at the Edge: Mobility-Aware Dynamic Service Placement for Mobile Edge Computing

HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness?

Large Language Models for Code Analysis: Do LLMs Really Do Their Job?

SWE-Together: Evaluating Coding Agents in Interactive User Sessions

SWE-Master: Unleashing the Potential of Software Engineering Agents via Post-Training

Deep API Learning

Understanding and Detecting Flaky Builds in GitHub Actions

Is "Better Data" Better than "Better Data Miners"? (On the Benefits of Tuning SMOTE for Defect Prediction)

ProofWright: Towards Agentic Formal Verification of CUDA

CoderUJB: An Executable and Unified Java Benchmark for Practical Programming Scenarios

Learning from the Test: Self-Referential Differential Testing for Deep RL Agents

Generalization or Memorization: Data Contamination and Trustworthy Evaluation for Large Language Models

Confucius Code Agent: Scalable Agent Scaffolding for Real-World Codebases

Human oversight of agentic systems in practice: Examining the oversight work, challenges, and heuristics of developers using software agents

Operator Packages, Proposer Strength, and Construction-Family Plateaus in Office-Scale Verified Search

PIPE-Cypher: Automatic Enterprise Benchmark Generation for Text-to-Cypher Systems

Poison Attack and Defense on Deep Source Code Processing Models

MalSkillBench: A Runtime-Verified Benchmark of Malicious Agent Skills

DRACO: Fine-Grained Credit Assignment with Dynamic Rubrics for Long-Horizon Agent Training

Scenario-Guided LLM-based Mobile App GUI Testing

Studying the Characteristics of AIOps Projects on GitHub

Investigating Explainability of Generative AI for Code through Scenario-based Design

Replications, Revisions, and Reanalyses: Managing Empirical Evidence in Software Engineering

ObliVul: Alert-Conditioned Safety Obligation Modeling and Bidirectional Counterfactual Validation for Code Vulnerability Detection

Towards Accountability for Machine Learning Datasets: Practices from Software Engineering and Infrastructure

Verification-Time Dependency on a Disappearing Evaluator

Predicting Program Exit Code with LLMs and Programming Language Semantics

GameDevBench: Evaluating Agentic Capabilities Through Game Development

UniDebugger: Hierarchical Multi-Agent Framework for Unified Software Debugging

Continuous Process-Level Evaluation for Evolving Enterprise AI Agent Skills

LLM-Enhanced Commit Message Generation via Issue Information: An Exploratory Study

StarCoder: may the source be with you!

WebCoderBench: Benchmarking Web Application Generation with Comprehensive and Interpretable Evaluation Metrics

A Large-Scale Survey on the Usability of AI Programming Assistants: Successes and Challenges

Bugs in Large Language Models Generated Code: An Empirical Study

WebCompass: Towards Multimodal Web Coding Evaluation for Code Language Models

PaperFit: Vision-in-the-Loop Typesetting Optimization for Scientific Documents

Repair Is Nearly Generation: Multilingual Program Repair with LLMs

Kimi-Dev: Agentless Training as Skill Prior for SWE-Agents

Software Engineering for AI-driven Building Operation

InteractBench: Benchmarking LLMs on Competitive Programming under Unrevealed Information

A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT

Teaching an Old LLM Secure Coding: Localized Preference Optimization on Distilled Preferences

UI2App: Benchmarking Visual Interaction Inference in Executable Web Application Generation

Learning from Mutants: Using Code Mutation to Learn and Monitor Invariants of a Cyber-Physical System

Planning-Driven Programming: A Large Language Model Programming Workflow

A Transformer-based Approach for Source Code Summarization

A Deep Dive into Large Language Models for Automated Bug Localization and Repair

Reading Between the Lines: Modeling User Behavior and Costs in AI-Assisted Programming

kRAIG: A Natural Language-Driven Agent for Automated DataOps Pipeline Generation

Adaptive Strategy Generation for Boundary Value Exploration Beyond Numeric Inputs

Learning to Solve and Verify: A Self-Play Framework for Code and Test Generation

Specification-first convergence with an AI coding agent: a case study of dismantling a core architectural invariant across 189 files in a 717k-line codebase with no test oracle and no human code review