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)

1,201 to 1,260 of 1,390

SWE-World: Building Software Engineering Agents in Docker-Free Environments
Shuang Sun, Huatong Song, Lisheng Huang +11
cs.SEcs.CLarXiv:2602.03419v12026
Scalable Distributed Simulation-Based Testing for Automated Driving Systems
Christian Geller, Benedikt Haas, Lutz Eckstein
cs.ROcs.DBcs.SEarXiv:2608.20904v12026
A Survey of Machine Learning for Big Code and Naturalness
Miltiadis Allamanis, Earl T. Barr, Premkumar Devanbu +1
cs.SEcs.LGcs.PLarXiv:1709.06182v22017
The Software Supply Chain as a Market for Lemons: A Multivocal Review of Trust Signal Collapse
Ranindya Paramitha, Christian Kästner, Laurie Williams
cs.CRcs.SEarXiv:2608.20678v12026
Generation of Web Apps with Agentic IDEs: An Empirical Assessment
Manuel Marceca, Maria Teresa Rossi, Leonardo Mariani
cs.SEarXiv:2608.20903v12026
AI-to-AI Code Reviews of GitHub Pull Requests
Niruthiha Selvanayagam, Taher A. Ghaleb
cs.SEarXiv:2608.21311v12026
AutoMOOSE: Use Case and Logical Views of Agentic Phase-Field Simulation Software
Sukriti Manna, Henry Chan, Subramanian Sankaranarayanan
cond-mat.mtrl-scics.SEarXiv:2608.20571v12026
Model Context Protocol (MCP) Tool Descriptions Are Smelly! Towards Improving AI Agent Efficiency with Augmented MCP Tool Descriptions
Mohammed Mehedi Hasan, Hao Li, Gopi Krishnan Rajbahadur +2
cs.SEcs.ETarXiv:2602.14878v32026
SlopCodeBench: Benchmarking How Coding Agents Degrade Over Long-Horizon Iterative Tasks
Gabriel Orlanski, Devjeet Roy, Alexander Yun +7
cs.SEcs.AIcs.CLarXiv:2603.24755v22026
FeatureBench: Benchmarking Agentic Coding for Complex Feature Development
Qixing Zhou, Jiacheng Zhang, Haiyang Wang +9
cs.SEcs.AIarXiv:2602.10975v12026
UniXcoder: Unified Cross-Modal Pre-training for Code Representation
Daya Guo, Shuai Lu, Nan Duan +3
cs.CLcs.PLcs.SEarXiv:2203.03850v12022
On the Time and Frequency Domain Representations of Signals for CPS Specification
Claudio Mandrioli, Drishti Yadav, Domenico Bianculli
cs.SEarXiv:2608.21167v12026
Composer 2 Technical Report
Cursor Research, :, Aaron Chan +53
cs.SEcs.LGarXiv:2603.24477v22026
Behavior Specification-Guided Program Synthesis for Binary Deobfuscation
Kangchen Zhu, Shangwen Wang, Zhiliang Tian +5
cs.SEarXiv:2608.20628v12026
Natural-Language Workflows Are Not Software Yet: Artifact-Driven Compilation for Reliable Agent Execution
Xiangzhe Xu, Hanxi Guo, Guangyu Shen +2
cs.SEarXiv:2608.21341v12026
AIDev: Studying AI Coding Agents on GitHub
Hao Li, Haoxiang Zhang, Ahmed E. Hassan
cs.SEcs.AIarXiv:2602.09185v12026
Human-AI Collaboration in Requirements Engineering: Evidence of the Negative Effect of LLMs on Requirements Inspection
Giovanna Broccia, Julian Frattini, Chetan Arora +4
cs.SEarXiv:2608.21298v12026
Beyond the Traceback: Using LLMs for Adaptive Explanations of Programming Errors
Alexandru-Radu Moraru, Shreyan Biswas, Ujwal Gadiraju
cs.SEcs.HCarXiv:2608.20896v12026
SWE-Pruner: Self-Adaptive Context Pruning for Coding Agents
Yuhang Wang, Yuling Shi, Mo Yang +7
cs.SEcs.CLarXiv:2601.16746v42026
A Survey on Large Language Models for Code Generation
Juyong Jiang, Fan Wang, Jiasi Shen +2
cs.CLcs.AIcs.SEarXiv:2406.00515v22024
Agent Skills: A Data-Driven Analysis of Claude Skills for Extending Large Language Model Functionality
George Ling, Shanshan Zhong, Richard Huang
cs.SEcs.SIarXiv:2602.08004v12026
Agent Skills in the Wild: An Empirical Study of Security Vulnerabilities at Scale
Yi Liu, Weizhe Wang, Ruitao Feng +5
cs.CRcs.AIcs.CLarXiv:2601.10338v12026
SWE-Skills-Bench: Do Agent Skills Actually Help in Real-World Software Engineering?
Tingxu Han, Yi Zhang, Wei Song +4
cs.SEcs.AIarXiv:2603.15401v12026
Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces
Mike A. Merrill, Alexander G. Shaw, Nicholas Carlini +82
cs.SEcs.AIarXiv:2601.11868v12026
Investigating Autonomous Agent Contributions in the Wild: Activity Patterns and Code Change over Time
Razvan Mihai Popescu, David Gros, Andrei Botocan +3
cs.SEcs.AIcs.LGarXiv:2604.00917v12026
Revision or Re-Solving? Decomposing Second-Pass Gains in Multi-LLM Pipelines
Jingjie Ning, Xueqi Li, Chengyu Yu
cs.SEcs.AIcs.CLarXiv:2604.01029v22026
Executing as You Generate: Hiding Execution Latency in LLM Code Interpreters
Zhensu Sun, Zhihao Lin, Zhi Chen +4
cs.PLcs.AIcs.SEarXiv:2604.00491v22026
GPA: Learning GUI Process Automation from Demonstrations
Zirui Zhao, Jun Hao Liew, Yan Yang +5
cs.CVcs.AIcs.SEarXiv:2604.01676v22026
Squeez: Task-Conditioned Tool-Output Pruning for Coding Agents
Ádám Kovács
cs.SEcs.AIarXiv:2604.04979v12026
Qualixar OS: A Universal Operating System for AI Agent Orchestration
Varun Pratap Bhardwaj
cs.AIcs.MAcs.SEarXiv:2604.06392v12026
SkVM: Revisiting Language VM for Skills across Heterogenous LLMs and Harnesses
Le Chen, Erhu Feng, Yubin Xia +1
cs.SEcs.LGarXiv:2604.03088v32026
Beyond Accuracy: Unveiling Inefficiency Patterns in Tool-Integrated Reasoning
Qisheng Su, Shiting Huang, Zhen Fang +3
cs.PFcs.SEarXiv:2604.05404v22026
QiMeng-PRepair: Precise Code Repair via Edit-Aware Reward Optimization
Changxin Ke, Rui Zhang, Jiaming Guo +10
cs.SEcs.LGarXiv:2604.05963v12026
Spec Kit Agents: Context-Grounded Agentic Workflows
Pardis Taghavi, Santosh Bhavani
cs.SEcs.AIcs.MAarXiv:2604.05278v12026
Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering
Chenyu Zhou, Huacan Chai, Wenteng Chen +18
cs.SEcs.MAarXiv:2604.08224v12026
Do AI Coding Agents Log Like Humans? An Empirical Study
Youssef Esseddiq Ouatiti, Mohammed Sayagh, Hao Li +1
cs.SEarXiv:2604.09409v12026
CodeTracer: Towards Traceable Agent States
Han Li, Yifan Yao, Letian Zhu +13
cs.SEcs.AIarXiv:2604.11641v32026
Sema Code: Decoupling AI Coding Agents into Programmable, Embeddable Infrastructure
Huacan Wang, Jie Zhou, Ningyan Zhu +8
cs.SEarXiv:2604.11045v12026
Dive into Claude Code: The Design Space of Today's and Future AI Agent Systems
Jiacheng Liu, Xiaohan Zhao, Xinyi Shang +1
cs.SEcs.AIcs.CLarXiv:2604.14228v22026
Don't Make Models Guess Security and Safety: Symbolic Guardrails for Domain-Specific AI Agents
Yining Hong, Yining She, Eunsuk Kang +2
cs.SEcs.AIcs.CRarXiv:2604.15579v22026
Precise Debugging Benchmark: Is Your Model Debugging or Regenerating?
Wang Bill Zhu, Miaosen Chai, Shangshang Wang +5
cs.SEcs.CLarXiv:2604.17338v42026
WebCompass: Towards Multimodal Web Coding Evaluation for Code Language Models
Xinping Lei, Xinyu Che, Junqi Xiong +16
cs.SEcs.AIarXiv:2604.18224v12026
OpenGame: Open Agentic Coding for Games
Yilei Jiang, Jinyuan Hu, Qianyin Xiao +8
cs.SEarXiv:2604.18394v12026
SWE-chat: Coding Agent Interactions From Real Users in the Wild
Joachim Baumann, Vishakh Padmakumar, Xiang Li +3
cs.AIcs.CYcs.SEarXiv:2604.20779v12026
PlayCoder: Making LLM-Generated GUI Code Playable
Zhiyuan Peng, Wei Tao, Xin Yin +3
cs.SEarXiv:2604.19742v12026
WebGen-R1: Incentivizing Large Language Models to Generate Functional and Aesthetic Websites with Reinforcement Learning
Juyong Jiang, Chenglin Cai, Chansung Park +4
cs.CLcs.LGcs.SEarXiv:2604.20398v12026
AI with Authority, from Application to Silicon
Jason Hickey
cs.SEcs.AIcs.ARarXiv:2608.21356v12026
PromptResponse: Optimizing Prompts for LLM Coding Tasks
Erik Thureck, Robert Kühnen, Tim Jacobowitz
cs.CLcs.AIcs.HCarXiv:2608.21074v12026
BC-Bench: Evaluating Agentic Engineering in a Domain-Specific Language for ERP
Haoran Sun, Klaus Marius Hansen
cs.SEcs.AIarXiv:2608.20851v12026
Temporal Validity on Real Software Histories: Eliminating Stale-Fact Errors in Code-Assistant Memory over GitHub Fixes
Neeraj Yadav
cs.SEcs.AIcs.CLarXiv:2608.20685v12026
Trustworthy RAG: An Evaluation Agent for Detecting Misinformation and Knowledge Poisoning in Generative AI Systems
Balkrishna Giri, Md Toufique Hasan, Jussi Rasku +2
cs.SEcs.AIcs.CLarXiv:2608.21095v12026
Making Deployments Safe at Meta: Health Checks for Continuous Change-Safety
Prakash KL, Anton Korenkov, Uttam Thakore +1
cs.SEcs.AIarXiv:2608.20513v12026
Large Language Models at the Intersection of Software Engineering and Software Security:An Evidence-Centered Structured Survey and Research Agenda
Wei Lin, Tao Zhou, Zhaofei Xie +1
cs.AIcs.SEarXiv:2608.21107v12026
Applying Anthropic Primitives at Large Enterprises: Harness Paradigm for Knowledge Work
George Juraj Salapa
cs.AIcs.SEarXiv:2608.20622v12026
SDAD: Spec-Driven Agentic Development for the AI-Native SDLC
Vu Hung Nguyen, Thanh Nguyen
cs.AIcs.SEarXiv:2608.20341v12026
Terminal Agents: A Survey of AI Agents in Command-Line Environments
Yi Bin, Xiaoyang Yuan, Haoxi Zeng +9
cs.AIcs.SEarXiv:2608.20485v12026
Safety Drift After Fine-Tuning: Evidence from High-Stakes Domains
Emaan Bilal Khan, Amy Winecoff, Miranda Bogen +1
cs.CYcs.SEarXiv:2604.24902v12026
Microservices: yesterday, today, and tomorrow
Nicola Dragoni, Saverio Giallorenzo, Alberto Lluch Lafuente +4
cs.SEarXiv:1606.04036v42016
Code World Model Preparedness Report
Daniel Song, Peter Ney, Cristina Menghini +21
cs.SEcs.AIarXiv:2605.00932v22026
Devign: Effective Vulnerability Identification by Learning Comprehensive Program Semantics via Graph Neural Networks
Yaqin Zhou, Shangqing Liu, Jingkai Siow +2
cs.SEcs.CRcs.LGarXiv:1909.03496v12019

Software Engineering

SWE-World: Building Software Engineering Agents in Docker-Free Environments

Scalable Distributed Simulation-Based Testing for Automated Driving Systems

A Survey of Machine Learning for Big Code and Naturalness

The Software Supply Chain as a Market for Lemons: A Multivocal Review of Trust Signal Collapse

Generation of Web Apps with Agentic IDEs: An Empirical Assessment

AI-to-AI Code Reviews of GitHub Pull Requests

AutoMOOSE: Use Case and Logical Views of Agentic Phase-Field Simulation Software

Model Context Protocol (MCP) Tool Descriptions Are Smelly! Towards Improving AI Agent Efficiency with Augmented MCP Tool Descriptions

SlopCodeBench: Benchmarking How Coding Agents Degrade Over Long-Horizon Iterative Tasks

FeatureBench: Benchmarking Agentic Coding for Complex Feature Development

UniXcoder: Unified Cross-Modal Pre-training for Code Representation

On the Time and Frequency Domain Representations of Signals for CPS Specification

Composer 2 Technical Report

Behavior Specification-Guided Program Synthesis for Binary Deobfuscation

Natural-Language Workflows Are Not Software Yet: Artifact-Driven Compilation for Reliable Agent Execution

AIDev: Studying AI Coding Agents on GitHub

Human-AI Collaboration in Requirements Engineering: Evidence of the Negative Effect of LLMs on Requirements Inspection

Beyond the Traceback: Using LLMs for Adaptive Explanations of Programming Errors

SWE-Pruner: Self-Adaptive Context Pruning for Coding Agents

A Survey on Large Language Models for Code Generation

Agent Skills: A Data-Driven Analysis of Claude Skills for Extending Large Language Model Functionality

Agent Skills in the Wild: An Empirical Study of Security Vulnerabilities at Scale

SWE-Skills-Bench: Do Agent Skills Actually Help in Real-World Software Engineering?

Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces

Investigating Autonomous Agent Contributions in the Wild: Activity Patterns and Code Change over Time

Revision or Re-Solving? Decomposing Second-Pass Gains in Multi-LLM Pipelines

Executing as You Generate: Hiding Execution Latency in LLM Code Interpreters

GPA: Learning GUI Process Automation from Demonstrations

Squeez: Task-Conditioned Tool-Output Pruning for Coding Agents

Qualixar OS: A Universal Operating System for AI Agent Orchestration

SkVM: Revisiting Language VM for Skills across Heterogenous LLMs and Harnesses

Beyond Accuracy: Unveiling Inefficiency Patterns in Tool-Integrated Reasoning

QiMeng-PRepair: Precise Code Repair via Edit-Aware Reward Optimization

Spec Kit Agents: Context-Grounded Agentic Workflows

Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering

Do AI Coding Agents Log Like Humans? An Empirical Study

CodeTracer: Towards Traceable Agent States

Sema Code: Decoupling AI Coding Agents into Programmable, Embeddable Infrastructure

Dive into Claude Code: The Design Space of Today's and Future AI Agent Systems

Don't Make Models Guess Security and Safety: Symbolic Guardrails for Domain-Specific AI Agents

Precise Debugging Benchmark: Is Your Model Debugging or Regenerating?

WebCompass: Towards Multimodal Web Coding Evaluation for Code Language Models

OpenGame: Open Agentic Coding for Games

SWE-chat: Coding Agent Interactions From Real Users in the Wild

PlayCoder: Making LLM-Generated GUI Code Playable

WebGen-R1: Incentivizing Large Language Models to Generate Functional and Aesthetic Websites with Reinforcement Learning

AI with Authority, from Application to Silicon

PromptResponse: Optimizing Prompts for LLM Coding Tasks

BC-Bench: Evaluating Agentic Engineering in a Domain-Specific Language for ERP

Temporal Validity on Real Software Histories: Eliminating Stale-Fact Errors in Code-Assistant Memory over GitHub Fixes

Trustworthy RAG: An Evaluation Agent for Detecting Misinformation and Knowledge Poisoning in Generative AI Systems

Making Deployments Safe at Meta: Health Checks for Continuous Change-Safety

Large Language Models at the Intersection of Software Engineering and Software Security:An Evidence-Centered Structured Survey and Research Agenda

Applying Anthropic Primitives at Large Enterprises: Harness Paradigm for Knowledge Work

SDAD: Spec-Driven Agentic Development for the AI-Native SDLC

Terminal Agents: A Survey of AI Agents in Command-Line Environments

Safety Drift After Fine-Tuning: Evidence from High-Stakes Domains

Microservices: yesterday, today, and tomorrow

Code World Model Preparedness Report

Devign: Effective Vulnerability Identification by Learning Comprehensive Program Semantics via Graph Neural Networks