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)

1,921 to 1,980 of 2,739

RepoST: Scalable Repository-Level Coding Environment Construction with Sandbox Testing
Yiqing Xie, Alex Xie, Divyanshu Sheth +3
cs.CLcs.SEarXiv:2503.07358v12025
Mitigating Error Propagation in Chain-of-Thought: A Tree-of-Thought Framework for Smart Contract Repair
Jingping Zhu, Hongping Wang, Xiaoqi Li
cs.CRcs.SEarXiv:2608.22345v12026
Estimating Inconsistency Response Surfaces under Uncertainty in Cyber-Physical System Development
Johannes Mäkelburg, Tim Schwabe, Maribel Acosta
cs.LGcs.SEeess.SYarXiv:2609.11331v12026
The Evolution of Binary Decompilation in the Modern Era: A Taxonomy, Literature Review, and Future Perspectives
Omar Abusabha, Sungjae Hwang
cs.SEcs.CRarXiv:2608.24955v12026
Disagree to Explore, Agree to Commit: Routing-Guided Test-Time Scaling for Software Agents
Kang Chen, Junjie Nian, Yixin Cao +1
cs.AIcs.SEarXiv:2608.22191v12026
ClarifyCodeBench: Evaluating LLMs on Clarifying Ambiguous Requirements for Code Generation
Zheng Fang, Dongming Jin, Yihong dong +4
cs.SEcs.AIarXiv:2607.00711v22026
Dexpler: Converting Android Dalvik Bytecode to Jimple for Static Analysis with Soot
Alexandre Bartel, Jacques Klein, Martin Monperrus +1
cs.SEarXiv:1205.3576v22012
PromptResponse: Optimizing Prompts for LLM Coding Tasks
Erik Thureck, Robert Kühnen, Tim Jacobowitz
cs.CLcs.AIcs.HCarXiv:2608.21074v12026
DomAgent: Leveraging Knowledge Graphs and Case-Based Reasoning for Domain-Specific Code Generation
Shuai Wang, Dhasarathy Parthasarathy, Robert Feldt +1
cs.AIcs.SEarXiv:2603.21430v22026
A Survey of Learning-based Automated Program Repair
Quanjun Zhang, Chunrong Fang, Yuxiang Ma +2
cs.SEarXiv:2301.03270v32023
Mayavi: a package for 3D visualization of scientific data
Prabhu Ramachandran, Gaël Varoquaux
cs.SEarXiv:1010.4891v12010
BatCoder: Self-Supervised Bidirectional Code-Documentation Learning via Back-Translation
Jingwen Xu, Yiyang Lu, Zisu Huang +9
cs.LGcs.AIcs.SEarXiv:2602.02554v12026
RepairAgent: An Autonomous, LLM-Based Agent for Program Repair
Islem Bouzenia, Premkumar Devanbu, Michael Pradel
cs.SEcs.AIarXiv:2403.17134v22024
Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses
Jiahang Lin, Shichun Liu, Chengjun Pan +8
cs.CLcs.SEarXiv:2604.25850v42026
QuSema: Detecting Silent Bugs in Quantum Libraries via Quantum-knowledge-enhanced Agents
Yujin Song, Kaining Zhang, Qixin Zhang +3
cs.SEcs.AIquant-pharXiv:2610.10258v12026
Object Detection for Graphical User Interface: Old Fashioned or Deep Learning or a Combination?
Jieshan Chen, Mulong Xie, Zhenchang Xing +4
cs.CVcs.HCcs.LGarXiv:2008.05132v22020
SoK: Are LLMs Reliable at Source Code Recovery? A Taxonomy and Empirical Evaluation
Varun Kohli, Lee Bing Cheng, Nur Hazim Ghazali +3
cs.CRcs.SEarXiv:2610.11556v12026
Automated Discovery of Process Models from Event Logs: Review and Benchmark
Adriano Augusto, Raffaele Conforti, Marlon Dumas +5
cs.SEarXiv:1705.02288v32017
SWE-Explore: Benchmarking How Coding Agents Explore Repositories
Shaoqiu Zhang, Yuhang Wang, Jialiang Liang +8
cs.SEcs.CLarXiv:2606.07297v12026
From Traceability to Justifiability: Accountability Structures in Agentic Software Engineering
Rashid Azarang
cs.SEarXiv:2608.23610v12026
TIPCODER: Reinforcement Learning Boosted Test-time Instruction Proposer for Code Generation
Minyu Chen, Sihao Wu, Ling-I Wu +5
cs.SEarXiv:2609.03309v12026
PQLS: A High-Performance Python Library for Steady-State Simulation of Open Quantum Systems
Evan Simanovskis, Raviraj Adve, Javane Rostampoor
cs.SEarXiv:2609.12309v12026
Don't Complete It! Preventing Unhelpful Code Completion for Productive and Sustainable Neural Code Completion Systems
Zhensu Sun, Xiaoning Du, Fu Song +4
cs.SEcs.AIarXiv:2209.05948v32022
An Empirical Study of Blockchain Repositories in GitHub
Ajoy Das, Gias Uddin, Guenther Ruhe
cs.CRcs.SEarXiv:2205.08087v12022
CODESIM: Multi-Agent Code Generation and Problem Solving through Simulation-Driven Planning and Debugging
Md. Ashraful Islam, Mohammed Eunus Ali, Md Rizwan Parvez
cs.CLcs.AIcs.SEarXiv:2502.05664v12025
Why Modern Open Source Projects Fail
Jailton Coelho, Marco Tulio Valente
cs.SEcs.CYarXiv:1707.02327v12017
Cogito, ergo sum: A Neurobiologically-Inspired Cognition-Memory-Growth System for Code Generation
Yanlong Li, Jindong Li, Qi Wang +3
cs.SEcs.AIarXiv:2501.18653v12025
Evaluating AGENTS.md: Are Repository-Level Context Files Helpful for Coding Agents?
Thibaud Gloaguen, Niels Mündler, Mark Müller +2
cs.SEcs.AIarXiv:2602.11988v22026
The Faiss library
Matthijs Douze, Alexandr Guzhva, Chengqi Deng +6
cs.LGcs.CVcs.SEarXiv:2401.08281v42024
Augmenting Smart Contract Decompiler Output through Fine-grained Dependency Analysis and LLM-facilitated Semantic Recovery
Zeqin Liao, Yuhong Nan, Zixu Gao +4
cs.SEarXiv:2501.08670v22025
CodeNet: A Large-Scale AI for Code Dataset for Learning a Diversity of Coding Tasks
Ruchir Puri, David S. Kung, Geert Janssen +14
cs.SEcs.AIarXiv:2105.12655v22021
D-Diff: An Interactive Environment for Adjusting Commit Boundaries Based on an Editable 3-way Diff
Daiki Muto, Takayoshi Ueno, Shinpei Hayashi
cs.SEarXiv:2608.22207v12026
Local Edits, Global Ripples: Replay-Informed Policy Adaptation for Workflow Synthesis
Manqing Mao, Hong Wang, Samson Koelle +8
cs.CLcs.SEarXiv:2609.12127v12026
Test-Driven Approaches to Software Engineering with Large Language Models: A Survey of Phases, Tasks, and Agent Skills
Yunhao Liang, Chengguang Gan, Ruixuan Ying +3
cs.SEarXiv:2609.12012v12026
Verus-SpecGym: An Agentic Environment for Evaluating Specification Autoformalization
Anmol Agarwal, Natalie Neamtu, Pranjal Aggarwal +6
cs.SEcs.AIcs.CLarXiv:2605.26457v12026
Harness or Model? Isolating the Harness Effect in Agentic Coding with a Contamination-Controlled Private Suite
Mohsen Arjmandi
cs.AIcs.CLcs.SEarXiv:2609.11987v12026
RosettaBitcoin: An Artifact-Backed Experience Report on Verification Infrastructure for Agent-Assisted Consensus Validators
Donavon Guyot
cs.SEarXiv:2609.01702v12026
Evaluating Local Language Model Agents for Reproducible Data Engineering: An Empirical Software Engineering Study of Mobility Workflows
Jorge García-Carrasco, Javier Sanchis, Alejandro Reina-Reina +2
cs.SEcs.AIcs.DBarXiv:2610.11482v12026
Maximum Resilience of Artificial Neural Networks
Chih-Hong Cheng, Georg Nührenberg, Harald Ruess
cs.LGcs.AIcs.LOarXiv:1705.01040v22017
MontiCore: a Framework for Compositional Development of Domain Specific Languages
Holger Krahn, Bernhard Rumpe, Stefan Völkel
cs.SEarXiv:1409.2367v12014
Building Program Vector Representations for Deep Learning
Lili Mou, Ge Li, Yuxuan Liu +4
cs.SEcs.LGcs.NEarXiv:1409.3358v12014
PyTy: Repairing Static Type Errors in Python
Yiu Wai Chow, Luca Di Grazia, Michael Pradel
cs.SEarXiv:2401.06619v12024
Big Code != Big Vocabulary: Open-Vocabulary Models for Source Code
Rafael-Michael Karampatsis, Hlib Babii, Romain Robbes +2
cs.SEarXiv:2003.07914v12020
How do Developers Test Android Applications?
Mario Linares Vasquez, Carlos Bernal-Cardenas, Kevin Moran +1
cs.SEarXiv:1801.06268v12018
On the Risks of using LLM-Generated Tests for Regression Testing
Mohammadali Charoosaei, Cedric Richter, Mike Papadakis
cs.SEarXiv:2610.11835v12026
StepCoder: Improve Code Generation with Reinforcement Learning from Compiler Feedback
Shihan Dou, Yan Liu, Haoxiang Jia +14
cs.SEcs.CLarXiv:2402.01391v22024
SimulaQron - A simulator for developing quantum internet software
Axel Dahlberg, Stephanie Wehner
quant-phcs.NIcs.SEarXiv:1712.08032v22017
Automatically Generating Commit Messages from Diffs using Neural Machine Translation
Siyuan Jiang, Ameer Armaly, Collin McMillan
cs.SEcs.CLarXiv:1708.09492v12017
From Natural Language Requirements to Graphical User Interfaces: Automated Prototyping and Verification with Pretrained Language Models
Kristian Kolthoff
cs.SEarXiv:2608.24749v12026
From Prompting to Engineering: A Research Agenda for Prompt Engineering in Software Engineering
Vincenzo De Martino, Giovanna Broccia, Fabiano Pecorelli +6
cs.SEarXiv:2609.02248v12026
Guidelines for the Search Strategy to Update Systematic Literature Reviews in Software Engineering
Claes Wohlin, Emilia Mendes, Katia Romero Felizardo +1
cs.SEarXiv:2006.05542v12020
CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution
Alex Gu, Baptiste Rozière, Hugh Leather +3
cs.SEcs.AIcs.LGarXiv:2401.03065v12024
Engineering Sustainable Agents: A Systematic Comparison of Agentic LLMs for Developer Workflows
Merve Astekin, Yan Naing Tun, Arda Goknil +5
cs.SEcs.MAarXiv:2610.03010v12026
Seven Failure Points When Engineering a Retrieval Augmented Generation System
Scott Barnett, Stefanus Kurniawan, Srikanth Thudumu +2
cs.SEcs.AIarXiv:2401.05856v12024
Programming Is Hard -- Or at Least It Used to Be: Educational Opportunities And Challenges of AI Code Generation
Brett A. Becker, Paul Denny, James Finnie-Ansley +3
cs.HCcs.AIcs.CYarXiv:2212.01020v12022
Designing Collaborative AI-Driven Workflows for Scientific Software Engineering
Akash Dhruv, Max Knobbe, Pedro Machado +1
cs.SEarXiv:2610.09995v12026
Automatic Generation of Programming Exercises and Code Explanations using Large Language Models
Sami Sarsa, Paul Denny, Arto Hellas +1
cs.SEcs.AIcs.CLarXiv:2206.11861v22022
Can LLMs Replace Manual Annotation of Software Engineering Artifacts?
Toufique Ahmed, Premkumar Devanbu, Christoph Treude +1
cs.SEcs.HCcs.LGarXiv:2408.05534v12024
Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security
Yuanchun Li, Hao Wen, Weijun Wang +22
cs.HCcs.AIcs.SEarXiv:2401.05459v22024
CodeRAG-Bench: Can Retrieval Augment Code Generation?
Zora Zhiruo Wang, Akari Asai, Xinyan Velocity Yu +4
cs.SEcs.CLarXiv:2406.14497v22024

Software Engineering

RepoST: Scalable Repository-Level Coding Environment Construction with Sandbox Testing

Mitigating Error Propagation in Chain-of-Thought: A Tree-of-Thought Framework for Smart Contract Repair

Estimating Inconsistency Response Surfaces under Uncertainty in Cyber-Physical System Development

The Evolution of Binary Decompilation in the Modern Era: A Taxonomy, Literature Review, and Future Perspectives

Disagree to Explore, Agree to Commit: Routing-Guided Test-Time Scaling for Software Agents

ClarifyCodeBench: Evaluating LLMs on Clarifying Ambiguous Requirements for Code Generation

Dexpler: Converting Android Dalvik Bytecode to Jimple for Static Analysis with Soot

PromptResponse: Optimizing Prompts for LLM Coding Tasks

DomAgent: Leveraging Knowledge Graphs and Case-Based Reasoning for Domain-Specific Code Generation

A Survey of Learning-based Automated Program Repair

Mayavi: a package for 3D visualization of scientific data

BatCoder: Self-Supervised Bidirectional Code-Documentation Learning via Back-Translation

RepairAgent: An Autonomous, LLM-Based Agent for Program Repair

Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses

QuSema: Detecting Silent Bugs in Quantum Libraries via Quantum-knowledge-enhanced Agents

Object Detection for Graphical User Interface: Old Fashioned or Deep Learning or a Combination?

SoK: Are LLMs Reliable at Source Code Recovery? A Taxonomy and Empirical Evaluation

Automated Discovery of Process Models from Event Logs: Review and Benchmark

SWE-Explore: Benchmarking How Coding Agents Explore Repositories

From Traceability to Justifiability: Accountability Structures in Agentic Software Engineering

TIPCODER: Reinforcement Learning Boosted Test-time Instruction Proposer for Code Generation

PQLS: A High-Performance Python Library for Steady-State Simulation of Open Quantum Systems

Don't Complete It! Preventing Unhelpful Code Completion for Productive and Sustainable Neural Code Completion Systems

An Empirical Study of Blockchain Repositories in GitHub

CODESIM: Multi-Agent Code Generation and Problem Solving through Simulation-Driven Planning and Debugging

Why Modern Open Source Projects Fail

Cogito, ergo sum: A Neurobiologically-Inspired Cognition-Memory-Growth System for Code Generation

Evaluating AGENTS.md: Are Repository-Level Context Files Helpful for Coding Agents?

The Faiss library

Augmenting Smart Contract Decompiler Output through Fine-grained Dependency Analysis and LLM-facilitated Semantic Recovery

CodeNet: A Large-Scale AI for Code Dataset for Learning a Diversity of Coding Tasks

D-Diff: An Interactive Environment for Adjusting Commit Boundaries Based on an Editable 3-way Diff

Local Edits, Global Ripples: Replay-Informed Policy Adaptation for Workflow Synthesis

Test-Driven Approaches to Software Engineering with Large Language Models: A Survey of Phases, Tasks, and Agent Skills

Verus-SpecGym: An Agentic Environment for Evaluating Specification Autoformalization

Harness or Model? Isolating the Harness Effect in Agentic Coding with a Contamination-Controlled Private Suite

RosettaBitcoin: An Artifact-Backed Experience Report on Verification Infrastructure for Agent-Assisted Consensus Validators

Evaluating Local Language Model Agents for Reproducible Data Engineering: An Empirical Software Engineering Study of Mobility Workflows

Maximum Resilience of Artificial Neural Networks

MontiCore: a Framework for Compositional Development of Domain Specific Languages

Building Program Vector Representations for Deep Learning

PyTy: Repairing Static Type Errors in Python

Big Code != Big Vocabulary: Open-Vocabulary Models for Source Code

How do Developers Test Android Applications?

On the Risks of using LLM-Generated Tests for Regression Testing

StepCoder: Improve Code Generation with Reinforcement Learning from Compiler Feedback

SimulaQron - A simulator for developing quantum internet software

Automatically Generating Commit Messages from Diffs using Neural Machine Translation

From Natural Language Requirements to Graphical User Interfaces: Automated Prototyping and Verification with Pretrained Language Models

From Prompting to Engineering: A Research Agenda for Prompt Engineering in Software Engineering

Guidelines for the Search Strategy to Update Systematic Literature Reviews in Software Engineering

CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution

Engineering Sustainable Agents: A Systematic Comparison of Agentic LLMs for Developer Workflows

Seven Failure Points When Engineering a Retrieval Augmented Generation System

Programming Is Hard -- Or at Least It Used to Be: Educational Opportunities And Challenges of AI Code Generation

Designing Collaborative AI-Driven Workflows for Scientific Software Engineering

Automatic Generation of Programming Exercises and Code Explanations using Large Language Models

Can LLMs Replace Manual Annotation of Software Engineering Artifacts?

Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security

CodeRAG-Bench: Can Retrieval Augment Code Generation?