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)

2,161 to 2,220 of 2,781

A Baseline Assessment for the Agentic Web Technology Stack
Vagner Figueredo de Santana, Diogo Cortiz
cs.AIcs.ETcs.SEarXiv:2610.13703v12026
AgentSWE: Can Coding Agents Build the Agent You Actually Want?
Jiahao Wang, Hongjin Qian, Yuyang Hu +2
cs.SEcs.AIcs.LGarXiv:2610.13361v12026
RepairLLaMA: Efficient Representations and Fine-Tuned Adapters for Program Repair
André Silva, Sen Fang, Martin Monperrus
cs.SEcs.LGarXiv:2312.15698v62023
Efficiency Hallucination: Formalizing and Measuring Behavioral Calibration in LLM-Based Code Optimization
Sarah Wilson, Gail Kaiser, Patrick Musau
cs.SEcs.AIarXiv:2609.14839v12026
Co-Modifying Application Code and Deployment Infrastructure: A Causal Study of AI Agent Pull Requests
Mohammad Wathiq Soualhi, Basem Suleiman
cs.SEcs.AIarXiv:2610.12849v12026
The Stochastic Deputy: Structural Tenant Isolation for Tool-Using LLM Agents
Mirza Samad Ahmed Baig, Syeda Anshrah Gillani, Asher Ali +1
cs.CRcs.AIcs.DBarXiv:2609.14780v12026
Predicting Usefulness of Code Review Comments using Textual Features and Developer Experience
Mohammad Masudur Rahman, Chanchal K. Roy, Raula G. Kula
cs.SEarXiv:1807.04485v12018
Improving ChatGPT Prompt for Code Generation
Chao Liu, Xuanlin Bao, Hongyu Zhang +4
cs.SEarXiv:2305.08360v12023
On the Effectiveness of Large Language Models in Domain-Specific Code Generation
Xiaodong Gu, Meng Chen, Yalan Lin +6
cs.SEarXiv:2312.01639v72023
Untangling Fine-Grained Code Changes
Martín Dias, Alberto Bacchelli, Georgios Gousios +2
cs.SEarXiv:1502.06757v12015
DevOps-Gym: Benchmarking AI Agents in Software DevOps Cycle
Yuheng Tang, Kaijie Zhu, Bonan Ruan +14
cs.SEcs.AIcs.CRarXiv:2601.20882v12026
SWE-TRACE: Optimizing Long-Horizon SWE Agents Through Rubric Process Reward Models and Heuristic Test-Time Scaling
Hao Han, Jin Xie, Xuehao Ma +5
cs.SEarXiv:2604.14820v12026
CoditT5: Pretraining for Source Code and Natural Language Editing
Jiyang Zhang, Sheena Panthaplackel, Pengyu Nie +2
cs.SEcs.LGarXiv:2208.05446v22022
SWE-Duel: Towards a Self-Scaling Arena for Coding Agents
Wei Minn, Zhensu Sun, Lwin Khin Shar +1
cs.CLcs.SEarXiv:2610.12569v12026
Not All Agents Are Equal: Code Quality and Post-Merge Maintenance Across Five Autonomous Coding Agents in the Wild
Obada Kraishan
cs.SEarXiv:2609.17598v12026
Failure as a Process: An Anatomy of CLI Coding Agent Trajectories
Xiangxin Zhao, Han Li, Shuaiting Li +4
cs.SEcs.AIarXiv:2607.09510v12026
A Performance-Sensitive Malware Detection System Using Deep Learning on Mobile Devices
Ruitao Feng, Sen Chen, Xiaofei Xie +3
cs.CRcs.SEarXiv:2005.04970v32020
Psychological Safety in Software Engineering Teams: A Systematic Mapping Study of Team Processes and Performance
Adnan Manzoor, Muhammad Azeem Akbar, Jussi Kasurinen +3
cs.SEarXiv:2610.08896v12026
Scenario-Based Compositional Statistical Model Checking for Safety Specifications
Abhinav Pomalapally, Arya Raeesi, Kevin Kai-Chun Chang +2
cs.LOcs.AIcs.ROarXiv:2610.05571v12026
Automatic Code Documentation Generation Using GPT-3
Junaed Younus Khan, Gias Uddin
cs.SEarXiv:2209.02235v12022
Same Patient, Different Order: Action-Level Reliability of Clinical LLM Agents Under Repeated Runs
Rohith Reddy Bellibatlu, Manpreet Singh, Zhoutian Han +1
cs.CLcs.AIcs.LGarXiv:2609.13582v12026
The Agentic Company OS: Substrate Inversion for Sustained Enterprise Agent Deployment
Oliver Aleksander Larsen, Mahyar T. Moghaddam
cs.SEcs.AIcs.MAarXiv:2609.13334v12026
Beyond Type-checking: Towards Holistic Evaluation of Formal Specification Generation
Srijith Nair, Aditya Vempaty, Jia Liu +1
cs.SEcs.AIarXiv:2610.10604v12026
Automatically Detecting and Fixing Deadlocks in Go Code with GoDDaR
Gustavo Feio, Jorge Coelho, Miguel Flor +2
cs.PLcs.DCcs.SEarXiv:2610.08962v12026
TestJack: Should you trust the results in coding benchmarks? Agentic Coding Benchmarks Auditing via Evaluator Evolution
Shuangjie Yao, Hao Wang, Koushik Sen +3
cs.SEcs.AIarXiv:2610.10619v12026
Analysis and Visualization of the Linux Kernel's Software Evolution Using the City Metaphor
Malte Hansen, Lukas Damerau, Moritz Bugla +2
cs.SEarXiv:2610.09910v12026
A Chat Assistant for Software Exploration in a 3D Software Visualization
Malte Hansen, Karim Issa, Wilhelm Hasselbring
cs.SEarXiv:2610.09901v12026
Spreadsheet Errors: What We Know. What We Think We Can Do
Raymond R. Panko
cs.SEcs.HCarXiv:0802.3457v12008
Implementing the Spec Growth Engine: Preventing Spec-Code Divergence, and Growing the Spec with Agents
Hartwig Grabowski
cs.SEarXiv:2610.11725v12026
Detecting HTTP Status Code Misuses in REST APIs via Static and Dynamic Analysis
Alix Decrop, Andrea Arcuri, Mike Papadakis +2
cs.SEarXiv:2609.12770v12026
Beyond Establishing the Four-Day Workweek: Understanding Adaptation and Long-Term Survival in an Agile Software Organization
Michael Neumann, Darja Šmite
cs.SEarXiv:2609.13089v12026
Evaluating Change Point Detection Methods for Software Performance Regression Analysis
Diego Elias Costa, Michele Tucci, Luca Traini +8
cs.SEarXiv:2610.09023v12026
Agentic Software Engineering: Foundational Pillars and a Research Roadmap
Ahmed E. Hassan, Hao Li, Dayi Lin +4
cs.SEcs.AIarXiv:2509.06216v32025
When Flaws Cascade: Understanding Vulnerabilities and Exploitation Chains in JavaScript Engines
Yuhan Ma, Jiongchi Yu, Xiaofei Xie +3
cs.CRcs.SEarXiv:2610.10844v12026
SpecGuard: Proving a Task Is Broken Before the Agent Cheats
Param Biyani, Krishnamurthy Dvijotham
cs.AIcs.LOcs.SEarXiv:2610.09159v12026
Mitigating Uncertainty Interactions in GenAI-based Adaptive Systems: Vision, Challenges and Preliminary Guidelines
Karthik Vaidhyanathan, Norha Villegas, Raffaela Mirandola +5
cs.SEarXiv:2610.08881v12026
From Monolith to Microservices: A Classification of Refactoring Approaches
Jonas Fritzsch, Justus Bogner, Alfred Zimmermann +1
cs.SEarXiv:1807.10059v22018
PolyCodeEval: Benchmarking Multilingual Code Generation from Functions to Repositories
Bowen Yang, Jiajun Jiang, Luxue Yu +3
cs.SEarXiv:2610.11618v12026
ParaRecover: A Process-Level Benchmark for Error Localization and Recovery in Parallel Tool-Use Agents
Bowen Guan, Zhentao Yin, Yanming Shen
cs.LGcs.SEarXiv:2609.12345v12026
Characterizing Overconfident Failure in LLM-Based Code Generation
Ravishka Rathnasuriya, Wei Yang
cs.SEcs.AIarXiv:2610.11300v12026
Who Pays the Review Cost? Triage, Fairness, and Accountability in AI-authored Pull Requests
Md Shamimur Rahman, Khairul Alam, Banani Roy +1
cs.SEarXiv:2610.11179v12026
An Investigation into the Use of Common Libraries in Android Apps
Li Li, Tegawendé F. Bissyandé, Jacques Klein +1
cs.SEarXiv:1511.06554v12015
Forms of LLM-Integrated Applications from LLM-Chats to Autonomous AI Agent System
Irene Weber
cs.CLcs.AIcs.SEarXiv:2610.11899v12026
What Drives Recovery in Agentic Text-to-Cypher? LAST-CQ: An LLM Agent Self-Refinement Framework
Ioannis Prokopiou, Athanasios Aidinis, Panagiotis-Christos Kyrmpatsos +1
cs.AIcs.CLcs.LGarXiv:2609.12746v12026
Evaluating Representation Learning of Code Changes for Predicting Patch Correctness in Program Repair
Haoye Tian, Kui Liu, Abdoul Kader Kaboreé +4
cs.SEarXiv:2008.02944v12020
Confidence-Gated Transductive Test Generation for Code Reranking
Sungjae Lee, Youngsik Yoon, Seockbean Song +3
cs.AIcs.CLcs.SEarXiv:2609.12489v12026
Cross-Provider Review as a Runtime Contract for Coding Agents: A Controlled Pilot and Fault-Injection Study
Bowen Xu, Boyu Chen
cs.SEcs.AIarXiv:2610.10961v12026
Has LLM Screening Performance Stalled in Software Engineering Systematic Reviews?
Aleksi Huotala, Miikka Kuutila, Mika Mäntylä
cs.SEcs.AIarXiv:2610.10633v12026
A Survey and Taxonomy of Self-Aware and Self-Adaptive Cloud Autoscaling Systems
Tao Chen, Rami Bahsoon, Xin Yao
cs.SEcs.DCarXiv:1609.03590v42016
An Insight into the Pull Requests of GitHub
Mohammad Masudur Rahman, Chanchal K. Roy
cs.SEarXiv:1807.01853v12018
Scan the Skill, Govern the Action: Composing Registry Verdicts with Runtime Consequence Control
Rohit Taneja, Travis Weber
cs.CRcs.SEarXiv:2609.12001v12026
Open Source Stewardship Communities: "We need you, but not your pull request"
Gregorio Robles, Daniel M. German
cs.SEarXiv:2609.12236v12026
Mission Performance: Automatic and Adaptive Race Pace Progression for Autonomous Racing
Giovanni Lambertini, Matteo Pini, Nicola Musiu +3
cs.ROcs.SEcs.SYarXiv:2609.12292v12026
Missing Dimensions: Integrating Human and Social Systems into Digital Twin Engineering
Francis Bordeleau, Mark van den Brand
cs.SEarXiv:2609.12131v12026
Investigating Developer-Reported Software Security Testing Challenges
Md Erfan, Ahmed Ryan, Md Rayhanur Rahman
cs.SEcs.CRarXiv:2609.12008v12026
Reality Is the Final Verifier: On Two Key Gaps in Agentic Software Engineering
Alexander Krentsel, Shubham Agarwal, Mert Cemri +5
cs.SEcs.AIarXiv:2609.12039v12026
Where Do the Tokens Go? Understanding and Reducing Costs in LLM Agents for Vulnerability Discovery
Li Lu, Yanjie Zhao, Hongjie Chen +1
cs.CRcs.SEarXiv:2610.11602v12026
Runnable Commit Untangling for Coding Agents
Jinfeng Jiang, Dongsun Kim, Dayi Lin +1
cs.SEcs.AIarXiv:2610.11593v12026
L2CEval: Evaluating Language-to-Code Generation Capabilities of Large Language Models
Ansong Ni, Pengcheng Yin, Yilun Zhao +11
cs.CLcs.LGcs.PLarXiv:2309.17446v22023
REPOFUSE: Repository-Level Code Completion with Fused Dual Context
Ming Liang, Xiaoheng Xie, Gehao Zhang +6
cs.SEcs.AIarXiv:2402.14323v22024

Software Engineering

A Baseline Assessment for the Agentic Web Technology Stack

AgentSWE: Can Coding Agents Build the Agent You Actually Want?

RepairLLaMA: Efficient Representations and Fine-Tuned Adapters for Program Repair

Efficiency Hallucination: Formalizing and Measuring Behavioral Calibration in LLM-Based Code Optimization

Co-Modifying Application Code and Deployment Infrastructure: A Causal Study of AI Agent Pull Requests

The Stochastic Deputy: Structural Tenant Isolation for Tool-Using LLM Agents

Predicting Usefulness of Code Review Comments using Textual Features and Developer Experience

Improving ChatGPT Prompt for Code Generation

On the Effectiveness of Large Language Models in Domain-Specific Code Generation

Untangling Fine-Grained Code Changes

DevOps-Gym: Benchmarking AI Agents in Software DevOps Cycle

SWE-TRACE: Optimizing Long-Horizon SWE Agents Through Rubric Process Reward Models and Heuristic Test-Time Scaling

CoditT5: Pretraining for Source Code and Natural Language Editing

SWE-Duel: Towards a Self-Scaling Arena for Coding Agents

Not All Agents Are Equal: Code Quality and Post-Merge Maintenance Across Five Autonomous Coding Agents in the Wild

Failure as a Process: An Anatomy of CLI Coding Agent Trajectories

A Performance-Sensitive Malware Detection System Using Deep Learning on Mobile Devices

Psychological Safety in Software Engineering Teams: A Systematic Mapping Study of Team Processes and Performance

Scenario-Based Compositional Statistical Model Checking for Safety Specifications

Automatic Code Documentation Generation Using GPT-3

Same Patient, Different Order: Action-Level Reliability of Clinical LLM Agents Under Repeated Runs

The Agentic Company OS: Substrate Inversion for Sustained Enterprise Agent Deployment

Beyond Type-checking: Towards Holistic Evaluation of Formal Specification Generation

Automatically Detecting and Fixing Deadlocks in Go Code with GoDDaR

TestJack: Should you trust the results in coding benchmarks? Agentic Coding Benchmarks Auditing via Evaluator Evolution

Analysis and Visualization of the Linux Kernel's Software Evolution Using the City Metaphor

A Chat Assistant for Software Exploration in a 3D Software Visualization

Spreadsheet Errors: What We Know. What We Think We Can Do

Implementing the Spec Growth Engine: Preventing Spec-Code Divergence, and Growing the Spec with Agents

Detecting HTTP Status Code Misuses in REST APIs via Static and Dynamic Analysis

Beyond Establishing the Four-Day Workweek: Understanding Adaptation and Long-Term Survival in an Agile Software Organization

Evaluating Change Point Detection Methods for Software Performance Regression Analysis

Agentic Software Engineering: Foundational Pillars and a Research Roadmap

When Flaws Cascade: Understanding Vulnerabilities and Exploitation Chains in JavaScript Engines

SpecGuard: Proving a Task Is Broken Before the Agent Cheats

Mitigating Uncertainty Interactions in GenAI-based Adaptive Systems: Vision, Challenges and Preliminary Guidelines

From Monolith to Microservices: A Classification of Refactoring Approaches

PolyCodeEval: Benchmarking Multilingual Code Generation from Functions to Repositories

ParaRecover: A Process-Level Benchmark for Error Localization and Recovery in Parallel Tool-Use Agents

Characterizing Overconfident Failure in LLM-Based Code Generation

Who Pays the Review Cost? Triage, Fairness, and Accountability in AI-authored Pull Requests

An Investigation into the Use of Common Libraries in Android Apps

Forms of LLM-Integrated Applications from LLM-Chats to Autonomous AI Agent System

What Drives Recovery in Agentic Text-to-Cypher? LAST-CQ: An LLM Agent Self-Refinement Framework

Evaluating Representation Learning of Code Changes for Predicting Patch Correctness in Program Repair

Confidence-Gated Transductive Test Generation for Code Reranking

Cross-Provider Review as a Runtime Contract for Coding Agents: A Controlled Pilot and Fault-Injection Study

Has LLM Screening Performance Stalled in Software Engineering Systematic Reviews?

A Survey and Taxonomy of Self-Aware and Self-Adaptive Cloud Autoscaling Systems

An Insight into the Pull Requests of GitHub

Scan the Skill, Govern the Action: Composing Registry Verdicts with Runtime Consequence Control

Open Source Stewardship Communities: "We need you, but not your pull request"

Mission Performance: Automatic and Adaptive Race Pace Progression for Autonomous Racing

Missing Dimensions: Integrating Human and Social Systems into Digital Twin Engineering

Investigating Developer-Reported Software Security Testing Challenges

Reality Is the Final Verifier: On Two Key Gaps in Agentic Software Engineering

Where Do the Tokens Go? Understanding and Reducing Costs in LLM Agents for Vulnerability Discovery

Runnable Commit Untangling for Coding Agents

L2CEval: Evaluating Language-to-Code Generation Capabilities of Large Language Models

REPOFUSE: Repository-Level Code Completion with Fused Dual Context