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)

1,261 to 1,320 of 1,389

SWE-WebDevBench: Evaluating Coding Agent Application Platforms as Virtual Software Agencies
Siddhant Saxena, Nilesh Trivedi, Vinayaka Jyothi
cs.MAcs.SEarXiv:2605.04637v12026
Model-Driven Development of Complex Software: A Research Roadmap
Robert France, Bernhard Rumpe
cs.SEarXiv:1409.6620v12014
Do not copy and paste! Rewriting strategies for code retrieval
Andrea Gurioli, Federico Pennino, Maurizio Gabbrielli
cs.SEcs.AIarXiv:2605.08299v12026
DeepTest: Automated Testing of Deep-Neural-Network-driven Autonomous Cars
Yuchi Tian, Kexin Pei, Suman Jana +1
cs.SEcs.AIcs.LGarXiv:1708.08559v22017
DeepXplore: Automated Whitebox Testing of Deep Learning Systems
Kexin Pei, Yinzhi Cao, Junfeng Yang +1
cs.LGcs.CRcs.SEarXiv:1705.06640v42017
MOCHA: Multi-Objective Chebyshev Annealing for Agent Skill Optimization
Md Mehrab Tanjim, Jayakumar Subramanian, Xiang Chen +6
cs.AIcs.LGcs.SEarXiv:2605.19330v12026
CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation
Shuai Lu, Daya Guo, Shuo Ren +19
cs.SEcs.CLarXiv:2102.04664v22021
Towards Evaluation Engineering: An Empirical Study of ML Evaluation Harnesses in the Wild
Zhimin Zhao, Zehao Wang, Abdul Ali Bangash +2
cs.SEcs.AIcs.LGarXiv:2605.24213v12026
Efficient and Scalable Provenance Tracking for LLM-Generated Code Snippets
Andrea Gurioli, Davide D'Ascenzo, Federico Pennino +2
cs.SEcs.AIcs.IRarXiv:2605.28510v22026
Benchmarks are Not Enough: RAMP for Runtime Assessing of Agentic Models in Production Systems
Yipeng Ouyang, Xin Huang, Bingjie Liu +3
cs.SEcs.AIarXiv:2605.27492v12026
REPOT: Recoverable Program-of-Thought via Checkpoint Repair
Parsa Mazaheri
cs.SEcs.AIcs.CLarXiv:2605.30052v12026
DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence
Daya Guo, Qihao Zhu, Dejian Yang +10
cs.SEcs.CLcs.LGarXiv:2401.14196v22024
A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT
Jules White, Quchen Fu, Sam Hays +6
cs.SEcs.AIarXiv:2302.11382v12023
LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code
Naman Jain, King Han, Alex Gu +7
cs.SEcs.CLcs.LGarXiv:2403.07974v22024
Combinatorial Synthesis: Scaling Code RLVR via Atomic Decomposition and Recombination
Jiasheng Zheng, Boxi Cao, Boxi Yu +6
cs.CLcs.SEarXiv:2605.31058v12026
FVSpec: Real-World Property-Based Tests as Lean Challenges
Quinn Dougherty, Max von Hippel, Simon Henniger +2
cs.SEcs.AIarXiv:2606.01008v22026
Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation
Jiawei Liu, Chunqiu Steven Xia, Yuyao Wang +1
cs.SEcs.CLcs.LGarXiv:2305.01210v32023
Lean4Agent: Formal Modeling and Verification for Agent Workflow and Trajectory
Ruida Wang, Jerry Huang, Pengcheng Wang +3
cs.AIcs.LGcs.LOarXiv:2606.06523v22026
Empirical Study on the Characteristics and Evolution of AI-usage in GitHub Repositories: Evidence from Code Comments
Abdullah Al Mujahid, Preetha Chatterjee, Mia Mohammad Imran
cs.SEarXiv:2606.06843v12026
PIPE-Cypher: Automatic Enterprise Benchmark Generation for Text-to-Cypher Systems
Suraj Ranganath, Anish Raghavendra
cs.LGcs.AIcs.DBarXiv:2606.08481v12026
Context Aware Computing for The Internet of Things: A Survey
Charith Perera, Arkady Zaslavsky, Peter Christen +1
cs.SEcs.HCarXiv:1305.0982v12013
Lean Refactor: Multi-Objective Controllable Proof Optimization via Agentic Strategy Search
Jialin Lu, Soonho Kong, Rodrigo Stehling +4
cs.LOcs.AIcs.CLarXiv:2605.20244v22026
SWE-bench Science: Can Coding Agents Resolve Engineering Tasks in Science?
Zhipeng Xu, Jiahao Lu, Yining Zheng +2
cs.CLcs.SEarXiv:2608.19799v12026
What Makes Software Issue Resolution Tasks Difficult for Agents?
Ebtesam Al-Haque, Brittany Johnson
cs.SEcs.AIcs.CLarXiv:2608.18280v12026
ARIS: Autonomous Research via Adversarial Multi-Agent Collaboration
Ruofeng Yang, Yongcan Li, Shuai Li
cs.SEcs.AIarXiv:2605.03042v12026
BenchEvolver: Frontier Task Synthesis via Solution-Centric Evolution
Yangzhen Wu, Aaron J. Li, Wenjie Ma +10
cs.SEcs.AIcs.CLarXiv:2606.01286v12026
Programming with Data: Test-Driven Data Engineering for Self-Improving LLMs from Raw Corpora
Chenkai Pan, Xinglong Xu, Yuhang Xu +6
cs.SEcs.AIarXiv:2604.24819v12026
DarwinX: Evolving Agent Harnesses Through Natural Selection
Yifan Zhang, Yutong Dai, Juntao Tan +9
cs.NEcs.AIcs.LGarXiv:2608.07545v12026
SemPlan: Benchmarking Structured Semantic Planning for LLM-Based Queries over Enterprise Data
Bruno Santos Teixeira
cs.AIcs.SEarXiv:2608.13612v12026
SkillForge: Self-Distilling Agents for Project-Specific Issue Resolution
Silin Chen, Han Li, Xiaodong Gu +2
cs.SEcs.AIarXiv:2608.18933v12026
SemaPLC: A Project-Grounded, Verification-Gated Agent Harness for PLC Code Generation
Yanlun Tu, Huacan Wang, Ziyue Zhou +10
cs.SEarXiv:2608.18565v12026
Adversarial Review: Structured Disagreement for Grounded Agentic Code Review
Eric S. Qiu, Joyce Gill
cs.AIcs.SEarXiv:2608.18167v12026
When Agents Coordinate: Measuring Coordination in Multi-Agent AI Coding
Giuseppe Destefanis, Tomaso Aste
cs.AIcs.SEarXiv:2608.16801v12026
The Recall Trap: A Recall-Maximizing Retriever Configuration Reduces Issue Resolution in Fixed-Budget Code Context
Alexander Adkins, Teimuraz Trapaidze
cs.SEcs.CLcs.IRarXiv:2608.14838v12026
Second Thought: Reasoning in Parallel as LLM Agents Act and Observe
Zhensu Sun, Chengran Yang, Yunbo Lyu +2
cs.AIcs.SEarXiv:2608.13667v12026
Grammar-Constrained Decoding Can Jailbreak LLMs into Generating Malicious Code
Yitong Zhang, Shiteng Lu, Jia Li
cs.CRcs.AIcs.CLarXiv:2606.11817v12026
When Gradients Collide: Failure Modes of Multi-Objective Prompt Optimization for LLM Judges
Parth Darshan, Abhishek Divekar
cs.CLcs.AIcs.LGarXiv:2605.26046v22026
SWE-bench: Can Language Models Resolve Real-World GitHub Issues?
Carlos E. Jimenez, John Yang, Alexander Wettig +4
cs.CLcs.AIcs.SEarXiv:2310.06770v32023
MicroPython and CircuitPython: Pythons Quiet Takeover of IoT and Robotics
Sayed Mahbub Hasan Amiri, Atiar Zahan
cs.PLcs.CLcs.SEarXiv:2608.18160v12026
Pre-Compiled Pipeline Shards for Distributed LLM Inference on Intel AI PC Fleets
Tate Berenbaum, Muthaiah Venkatachalam
cs.DCcs.AIcs.SEarXiv:2608.19147v12026
One Gate Is Not Enough: Composing Stateful Pre-Action Controls for Agentic AI
Gaston Besanson
cs.SEcs.AIcs.CYarXiv:2608.18360v12026
ImageJ2: ImageJ for the next generation of scientific image data
Curtis T. Rueden, Johannes Schindelin, Mark C. Hiner +4
cs.SEq-bio.QMarXiv:1701.05940v42017
Grouping the Stochastic Machine: Precision, Not Capability, as the Frontier Metric for AI Systems
George Andrikopoulos
cs.AIcs.CYcs.LGarXiv:2608.19140v12026
Tuning the Stochastic Machine: A Systems Engineer's Operating Model for Human-AI Engineering
George Andrikopoulos
cs.AIcs.SEarXiv:2608.19125v12026
Metrics That Write Themselves: Evolving an Evaluator from Its Own Blind Spots
Xing Zhang, Yanwei Cui, Guanghui Wang +2
cs.AIcs.CLcs.SEarXiv:2608.18744v12026
Securing AI-Generated Code: A Just-in-Time Vulnerability Detection and Remediation Pipeline
Mikhail Surikov
cs.CRcs.AIcs.SEarXiv:2608.16187v12026
Too Sure to Be Safe: Model Calibration for Reliable Log Anomaly Detection
Bin Li, Dongdong Wang, Siyang Lu
cs.LGcs.AIcs.SEarXiv:2608.17965v12026
What Aggregate Scores Miss: Measuring Item-Level Regressions in Commercial LLM API Migrations
Xiaonan Xu, Wenjing Wu
cs.SEcs.AIcs.CLarXiv:2608.17719v12026
No Resource, No Benchmarks, No Problem? Evaluating and Improving LLMs for Code Generation in No-Resource Languages
Alessandro Giagnorio, Alberto Martin-Lopez, Gabriele Bavota
cs.SEarXiv:2606.16827v12026
A Benchmark and Framework for Evaluating Next Action Predictions in Spreadsheets
Tejas Agrawal, Vu Le, Sumit Gulwani +1
cs.SEcs.AIcs.HCarXiv:2606.13802v12026
When Uncertainty Isn't Enough: An Empirical Study of Self-Correction in Code Generation
Pranav Rakasi, Maanas Lalwani, Arnav Srivastava +4
cs.AIcs.LGcs.SEarXiv:2608.14659v12026
When Agentic Executions Fail: Detecting and Localizing Runtime Faults from Telemetry
Chenkai Zhang, Yiran Li, Yifang Tian +2
cs.AIcs.SEarXiv:2608.14680v12026
Summaries:한국어
Evaluating Agentic Code Repair Capabilities in Distributed Systems
Yibo Yan, Huijuan Wang, Junzhou He +4
cs.SEcs.AIcs.DCarXiv:2608.14863v12026
PandasCorpus: A Resource of Real-World Pandas Workflows and Usage Patterns
Syrym Abdikhan, Mazhar Hameed
cs.SEcs.LGarXiv:2608.14742v12026
WeSCE: A Benchmark for Measuring Security Drift in LLM-Driven Code Editing
Zhiyu Zhang, Tingyue Wen, Senke Sun +2
cs.CRcs.AIcs.SEarXiv:2608.15092v12026
FAPO: Fully Automated Prompt Optimization of Multi-Step LLM Pipelines
Paul Kassianik, Baturay Saglam, Huaibo Zhao +4
cs.SEcs.AIarXiv:2606.19605v22026
OpenRath: Session-Centered Runtime State for Agent Systems
Fukang Wen, Zhijie Wang, Ruilin Xu
cs.SEcs.PLarXiv:2606.19409v12026
An Exploratory Case Study of LLM-Assisted Refactoring and Gameplay Feature Generation in an Endless Runner Game
Jan Wunderlich, Markus Kleffmann, Sebastian Lempert
cs.SEcs.AIarXiv:2606.21171v12026
Causal Discovery in the Era of Agents
Yujia Zheng, Vishal Verma, Mantej Gill +3
cs.AIcs.LGcs.SEarXiv:2606.23608v12026
EnterpriseClawBench: Benchmarking Agents from Real Workplace Sessions
Jincheng Zhong, Weizhi Wang, Che Jiang +5
cs.CLcs.SEarXiv:2606.23654v12026

Software Engineering

SWE-WebDevBench: Evaluating Coding Agent Application Platforms as Virtual Software Agencies

Model-Driven Development of Complex Software: A Research Roadmap

Do not copy and paste! Rewriting strategies for code retrieval

DeepTest: Automated Testing of Deep-Neural-Network-driven Autonomous Cars

DeepXplore: Automated Whitebox Testing of Deep Learning Systems

MOCHA: Multi-Objective Chebyshev Annealing for Agent Skill Optimization

CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation

Towards Evaluation Engineering: An Empirical Study of ML Evaluation Harnesses in the Wild

Efficient and Scalable Provenance Tracking for LLM-Generated Code Snippets

Benchmarks are Not Enough: RAMP for Runtime Assessing of Agentic Models in Production Systems

REPOT: Recoverable Program-of-Thought via Checkpoint Repair

DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence

A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT

LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code

Combinatorial Synthesis: Scaling Code RLVR via Atomic Decomposition and Recombination

FVSpec: Real-World Property-Based Tests as Lean Challenges

Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation

Lean4Agent: Formal Modeling and Verification for Agent Workflow and Trajectory

Empirical Study on the Characteristics and Evolution of AI-usage in GitHub Repositories: Evidence from Code Comments

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

Context Aware Computing for The Internet of Things: A Survey

Lean Refactor: Multi-Objective Controllable Proof Optimization via Agentic Strategy Search

SWE-bench Science: Can Coding Agents Resolve Engineering Tasks in Science?

What Makes Software Issue Resolution Tasks Difficult for Agents?

ARIS: Autonomous Research via Adversarial Multi-Agent Collaboration

BenchEvolver: Frontier Task Synthesis via Solution-Centric Evolution

Programming with Data: Test-Driven Data Engineering for Self-Improving LLMs from Raw Corpora

DarwinX: Evolving Agent Harnesses Through Natural Selection

SemPlan: Benchmarking Structured Semantic Planning for LLM-Based Queries over Enterprise Data

SkillForge: Self-Distilling Agents for Project-Specific Issue Resolution

SemaPLC: A Project-Grounded, Verification-Gated Agent Harness for PLC Code Generation

Adversarial Review: Structured Disagreement for Grounded Agentic Code Review

When Agents Coordinate: Measuring Coordination in Multi-Agent AI Coding

The Recall Trap: A Recall-Maximizing Retriever Configuration Reduces Issue Resolution in Fixed-Budget Code Context

Second Thought: Reasoning in Parallel as LLM Agents Act and Observe

Grammar-Constrained Decoding Can Jailbreak LLMs into Generating Malicious Code

When Gradients Collide: Failure Modes of Multi-Objective Prompt Optimization for LLM Judges

SWE-bench: Can Language Models Resolve Real-World GitHub Issues?

MicroPython and CircuitPython: Pythons Quiet Takeover of IoT and Robotics

Pre-Compiled Pipeline Shards for Distributed LLM Inference on Intel AI PC Fleets

One Gate Is Not Enough: Composing Stateful Pre-Action Controls for Agentic AI

ImageJ2: ImageJ for the next generation of scientific image data

Grouping the Stochastic Machine: Precision, Not Capability, as the Frontier Metric for AI Systems

Tuning the Stochastic Machine: A Systems Engineer's Operating Model for Human-AI Engineering

Metrics That Write Themselves: Evolving an Evaluator from Its Own Blind Spots

Securing AI-Generated Code: A Just-in-Time Vulnerability Detection and Remediation Pipeline

Too Sure to Be Safe: Model Calibration for Reliable Log Anomaly Detection

What Aggregate Scores Miss: Measuring Item-Level Regressions in Commercial LLM API Migrations

No Resource, No Benchmarks, No Problem? Evaluating and Improving LLMs for Code Generation in No-Resource Languages

A Benchmark and Framework for Evaluating Next Action Predictions in Spreadsheets

When Uncertainty Isn't Enough: An Empirical Study of Self-Correction in Code Generation

When Agentic Executions Fail: Detecting and Localizing Runtime Faults from Telemetry

Evaluating Agentic Code Repair Capabilities in Distributed Systems

PandasCorpus: A Resource of Real-World Pandas Workflows and Usage Patterns

WeSCE: A Benchmark for Measuring Security Drift in LLM-Driven Code Editing

FAPO: Fully Automated Prompt Optimization of Multi-Step LLM Pipelines

OpenRath: Session-Centered Runtime State for Agent Systems

An Exploratory Case Study of LLM-Assisted Refactoring and Gameplay Feature Generation in an Endless Runner Game

Causal Discovery in the Era of Agents

EnterpriseClawBench: Benchmarking Agents from Real Workplace Sessions