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)

2,461 to 2,520 of 2,806

To Add Is Machine, To Delete Is Human: Measuring and Mitigating Deletion Avoidance in LLM Code Editing
Amir M. Ebrahimi, Mohammed Mehedi Hasan, Aaditya Bhatia +2
cs.SEcs.AIcs.LGarXiv:2607.28887v12026
Efficient and Scalable Provenance Tracking for LLM-Generated Code Snippets
Andrea Gurioli, Davide D'Ascenzo, Federico Pennino +2
cs.SEcs.AIcs.IRarXiv:2605.28510v22026
R$^3$-SQL: Ranking Reward and Resampling for Text-to-SQL
Hojae Han, Yeonseok Jeong, Seung-won Hwang +2
cs.SEcs.AIcs.CLarXiv:2604.25325v12026
From Human-Centric to Agentic Code Review: The Impact of Different Generations of Generative AI Technology on Review Quality
Suzhen Zhong, Shayan Noei, Bram Adams +1
cs.SEarXiv:2607.13196v12026
BC-Bench: Evaluating Agentic Engineering in a Domain-Specific Language for ERP
Haoran Sun, Klaus Marius Hansen
cs.SEcs.AIarXiv:2608.20851v12026
Making Deployments Safe at Meta: Health Checks for Continuous Change-Safety
Prakash KL, Anton Korenkov, Uttam Thakore +1
cs.SEcs.AIarXiv:2608.20513v12026
Ouroboros: A Self-Developing Frontier Coding Agent with Reviewed Core Evolution
Anton Razzhigaev, Andrei Gritsaev, Andrei Kaznacheev +3
cs.SEcs.AIarXiv:2608.08311v22026
Spec Kit Agents: Context-Grounded Agentic Workflows
Pardis Taghavi, Santosh Bhavani
cs.SEcs.AIcs.MAarXiv:2604.05278v12026
Inside the Scaffold: A Source-Code Taxonomy of Coding Agent Architectures
Benjamin Rombaut
cs.SEcs.AIcs.ETarXiv:2604.03515v22026
Lossless Tensor Compression as Program Synthesis
Jieke Shi, Junda He, Wenjia Jiang +11
cs.SEcs.AIcs.PLarXiv:2608.02162v12026
Library Drift: Diagnosing and Fixing a Silent Failure Mode in Self-Evolving LLM Skill Libraries
Xing Zhang, Yanwei Cui, Guanghui Wang +4
cs.AIcs.CLcs.SEarXiv:2605.19576v32026
Graphectory Viewer: A Tool for Process-Centric Analysis of Agentic Software Trajectories
Charlie Jyu, Shuyang Liu, Reyhaneh Jabbarvand
cs.SEcs.AIarXiv:2608.17195v12026
TDD-Agent: Test-Driven Reasoning for Code Generation
Hongyue Yu, Kefan Li, Jiakun Li +4
cs.SEcs.AIarXiv:2608.16742v12026
The Working Set of a Coding Agent: Coherence Debt in Repository-Scale Tasks
Bardia Mohammadi, Lars Klein, Aman Chadha +2
cs.SEcs.LGarXiv:2608.16630v12026
Human-AI Synergy in Agentic Code Review
Suzhen Zhong, Shayan Noei, Ying Zou +1
cs.SEarXiv:2603.15911v12026
Are Performance-Optimization Benchmarks Reliably Measuring Coding Agents?
Zhi Chen, Zhensu Sun, Yuling Shi +2
cs.SEcs.AIarXiv:2607.01211v12026
Verified Learning for Compiler Optimization: An LLM-Guided Architecture with Formal Control
Dev Pratap Singh, Rong Feng, Suman Saha
cs.SEarXiv:2609.27214v12026
FullStack-Agent: Enhancing Agentic Full-Stack Web Coding via Development-Oriented Testing and Repository Back-Translation
Zimu Lu, Houxing Ren, Yunqiao Yang +4
cs.SEcs.CLcs.CVarXiv:2602.03798v12026
PandasCorpus: A Resource of Real-World Pandas Workflows and Usage Patterns
Syrym Abdikhan, Mazhar Hameed
cs.SEcs.LGarXiv:2608.14742v12026
Second Thought: Reasoning in Parallel as LLM Agents Act and Observe
Zhensu Sun, Chengran Yang, Yunbo Lyu +2
cs.AIcs.SEarXiv:2608.13667v12026
Composer 2 Technical Report
Cursor Research, :, Aaron Chan +53
cs.SEcs.LGarXiv:2603.24477v22026
OpenComputer: Verifiable Software Worlds for Computer-Use Agents
Jinbiao Wei, Qianran Ma, Yilun Zhao +4
cs.AIcs.SEarXiv:2605.19769v12026
IQuest-Coder-V1 Technical Report
Jian Yang, Wei Zhang, Shawn Guo +35
cs.AIcs.CLcs.SEarXiv:2603.16733v12026
ClawMark: A Living-World Benchmark for Multi-Turn, Multi-Day, Multimodal Coworker Agents
Fanqing Meng, Lingxiao Du, Zijian Wu +46
cs.CVcs.SEarXiv:2604.23781v22026
SABER: Benchmarking Operational Safety of LLM Coding Agents in Stateful Project Workspaces
Qi Hu, Yifeng Tang, Qinghua Wang +7
cs.SEcs.CRarXiv:2606.01317v12026
Structurally Aligned Subtask-Level Memory for Software Engineering Agents
Kangning Shen, Jingyuan Zhang, Chenxi Sun +2
cs.SEcs.AIarXiv:2602.21611v12026
Diffusion Templates: A Unified Plugin Framework for Controllable Diffusion
Zhongjie Duan, Hong Zhang, Yingda Chen
cs.LGcs.AIcs.CVarXiv:2604.24351v12026
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
CodeCircuit: Toward Inferring LLM-Generated Code Correctness via Attribution Graphs
Yicheng He, Zheng Zhao, Zhou Kaiyu +3
cs.SEcs.AIarXiv:2602.07080v12026
SkVM: Revisiting Language VM for Skills across Heterogenous LLMs and Harnesses
Le Chen, Erhu Feng, Yubin Xia +1
cs.SEcs.LGarXiv:2604.03088v32026
Squeez: Task-Conditioned Tool-Output Pruning for Coding Agents
Ádám Kovács
cs.SEcs.AIarXiv:2604.04979v12026
Solver-Aided Verification of Policy Compliance in Tool-Augmented LLM Agents
Cailin Winston, Claris Winston, René Just
cs.SEcs.AIarXiv:2603.20449v12026
A Survey on Code Generation with LLM-based Agents
Yihong Dong, Xue Jiang, Jiaru Qian +4
cs.SEcs.AIcs.CLarXiv:2508.00083v22025
BeyondSWE: Can Current Code Agent Survive Beyond Single-Repo Bug Fixing?
Guoxin Chen, Fanzhe Meng, Jiale Zhao +12
cs.CLcs.SEarXiv:2603.03194v22026
AIDev: Studying AI Coding Agents on GitHub
Hao Li, Haoxiang Zhang, Ahmed E. Hassan
cs.SEcs.AIarXiv:2602.09185v12026
LongCLI-Bench: A Preliminary Benchmark and Study for Long-horizon Agentic Programming in Command-Line Interfaces
Yukang Feng, Jianwen Sun, Zelai Yang +16
cs.SEcs.MAarXiv:2602.14337v22026
How AI Coding Agents Modify Code: A Large-Scale Study of GitHub Pull Requests
Daniel Ogenrwot, John Businge
cs.SEcs.AIarXiv:2601.17581v32026
Tokenomics: Quantifying Where Tokens Are Used in Agentic Software Engineering
Mohamad Salim, Jasmine Latendresse, SayedHassan Khatoonabadi +1
cs.SEcs.AIcs.MAarXiv:2601.14470v12026
AI IDEs or Autonomous Agents? Measuring the Impact of Coding Agents on Software Development
Shyam Agarwal, Hao He, Bogdan Vasilescu
cs.SEarXiv:2601.13597v22026
Guidelines to Prompt Large Language Models for Code Generation: An Empirical Characterization
Alessandro Midolo, Alessandro Giagnorio, Fiorella Zampetti +3
cs.SEarXiv:2601.13118v12026
LLM Hallucinations in Practical Code Generation: Phenomena, Mechanism, and Mitigation
Ziyao Zhang, Yanlin Wang, Chong Wang +2
cs.SEcs.AIcs.CLarXiv:2409.20550v22024
AgentTrace: A Structured Logging Framework for Agent System Observability
Adam AlSayyad, Kelvin Yuxiang Huang, Richik Pal
cs.SEcs.AIarXiv:2602.10133v12026
Regression Language Models for Code
Yash Akhauri, Xingyou Song, Arissa Wongpanich +2
cs.CLcs.AIcs.LGarXiv:2509.26476v32025
RM -RF: Reward Model for Run-Free Unit Test Evaluation
Elena Bruches, Daniil Grebenkin, Mikhail Klementev +8
cs.SEcs.LGarXiv:2601.13097v12026
RepoAudit: An Autonomous LLM-Agent for Repository-Level Code Auditing
Jinyao Guo, Chengpeng Wang, Xiangzhe Xu +2
cs.SEcs.PLarXiv:2501.18160v32025
Vulnerability Detection with Code Language Models: How Far Are We?
Yangruibo Ding, Yanjun Fu, Omniyyah Ibrahim +6
cs.SEcs.CLarXiv:2403.18624v22024
Evaluating Agent-based Program Repair at Google
Pat Rondon, Renyao Wei, José Cambronero +5
cs.SEcs.AIarXiv:2501.07531v12025
Multi-SWE-bench: A Multilingual Benchmark for Issue Resolving
Daoguang Zan, Zhirong Huang, Wei Liu +16
cs.SEcs.AIcs.CLarXiv:2504.02605v12025
Code to Think, Think to Code: A Survey on Code-Enhanced Reasoning and Reasoning-Driven Code Intelligence in LLMs
Dayu Yang, Tianyang Liu, Daoan Zhang +8
cs.CLcs.AIcs.LGarXiv:2502.19411v12025
CodeCoR: An LLM-Based Self-Reflective Multi-Agent Framework for Code Generation
Ruwei Pan, Hongyu Zhang, Chao Liu
cs.SEarXiv:2501.07811v22025
LeetCodeDataset: A Temporal Dataset for Robust Evaluation and Efficient Training of Code LLMs
Yunhui Xia, Wei Shen, Yan Wang +5
cs.LGcs.CLcs.SEarXiv:2504.14655v12025
Beyond Functional Correctness: Exploring Hallucinations in LLM-Generated Code
Fang Liu, Yang Liu, Lin Shi +5
cs.SEcs.AIarXiv:2404.00971v32024
Human-AI Collaboration for Multi-Line Task Adjustment Using Local Large Language Models and a Digital Twin
Teng-Hsien Ko, Chin-Te Lin
cs.SEarXiv:2609.29061v12026
FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance
Lingjiao Chen, Matei Zaharia, James Zou
cs.LGcs.AIcs.CLarXiv:2305.05176v12023
CrossCodeEval: A Diverse and Multilingual Benchmark for Cross-File Code Completion
Yangruibo Ding, Zijian Wang, Wasi Uddin Ahmad +8
cs.LGcs.CLcs.SEarXiv:2310.11248v22023
Can ChatGPT replace StackOverflow? A Study on Robustness and Reliability of Large Language Model Code Generation
Li Zhong, Zilong Wang
cs.CLcs.AIcs.SEarXiv:2308.10335v52023
Structured Chain-of-Thought Prompting for Code Generation
Jia Li, Ge Li, Yongmin Li +1
cs.SEcs.CLarXiv:2305.06599v32023
A New Era in Software Security: Towards Self-Healing Software via Large Language Models and Formal Verification
Norbert Tihanyi, Ridhi Jain, Yiannis Charalambous +3
cs.SEcs.AIcs.FLarXiv:2305.14752v22023
Large Language Models for Software Engineering: Survey and Open Problems
Angela Fan, Beliz Gokkaya, Mark Harman +4
cs.SEarXiv:2310.03533v42023
Impact of Code Language Models on Automated Program Repair
Nan Jiang, Kevin Liu, Thibaud Lutellier +1
cs.SEarXiv:2302.05020v32023

Software Engineering

To Add Is Machine, To Delete Is Human: Measuring and Mitigating Deletion Avoidance in LLM Code Editing

Efficient and Scalable Provenance Tracking for LLM-Generated Code Snippets

R$^3$-SQL: Ranking Reward and Resampling for Text-to-SQL

From Human-Centric to Agentic Code Review: The Impact of Different Generations of Generative AI Technology on Review Quality

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

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

Ouroboros: A Self-Developing Frontier Coding Agent with Reviewed Core Evolution

Spec Kit Agents: Context-Grounded Agentic Workflows

Inside the Scaffold: A Source-Code Taxonomy of Coding Agent Architectures

Lossless Tensor Compression as Program Synthesis

Library Drift: Diagnosing and Fixing a Silent Failure Mode in Self-Evolving LLM Skill Libraries

Graphectory Viewer: A Tool for Process-Centric Analysis of Agentic Software Trajectories

TDD-Agent: Test-Driven Reasoning for Code Generation

The Working Set of a Coding Agent: Coherence Debt in Repository-Scale Tasks

Human-AI Synergy in Agentic Code Review

Are Performance-Optimization Benchmarks Reliably Measuring Coding Agents?

Verified Learning for Compiler Optimization: An LLM-Guided Architecture with Formal Control

FullStack-Agent: Enhancing Agentic Full-Stack Web Coding via Development-Oriented Testing and Repository Back-Translation

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

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

Composer 2 Technical Report

OpenComputer: Verifiable Software Worlds for Computer-Use Agents

IQuest-Coder-V1 Technical Report

ClawMark: A Living-World Benchmark for Multi-Turn, Multi-Day, Multimodal Coworker Agents

SABER: Benchmarking Operational Safety of LLM Coding Agents in Stateful Project Workspaces

Structurally Aligned Subtask-Level Memory for Software Engineering Agents

Diffusion Templates: A Unified Plugin Framework for Controllable Diffusion

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

CodeCircuit: Toward Inferring LLM-Generated Code Correctness via Attribution Graphs

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

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

Solver-Aided Verification of Policy Compliance in Tool-Augmented LLM Agents

A Survey on Code Generation with LLM-based Agents

BeyondSWE: Can Current Code Agent Survive Beyond Single-Repo Bug Fixing?

AIDev: Studying AI Coding Agents on GitHub

LongCLI-Bench: A Preliminary Benchmark and Study for Long-horizon Agentic Programming in Command-Line Interfaces

How AI Coding Agents Modify Code: A Large-Scale Study of GitHub Pull Requests

Tokenomics: Quantifying Where Tokens Are Used in Agentic Software Engineering

AI IDEs or Autonomous Agents? Measuring the Impact of Coding Agents on Software Development

Guidelines to Prompt Large Language Models for Code Generation: An Empirical Characterization

LLM Hallucinations in Practical Code Generation: Phenomena, Mechanism, and Mitigation

AgentTrace: A Structured Logging Framework for Agent System Observability

Regression Language Models for Code

RM -RF: Reward Model for Run-Free Unit Test Evaluation

RepoAudit: An Autonomous LLM-Agent for Repository-Level Code Auditing

Vulnerability Detection with Code Language Models: How Far Are We?

Evaluating Agent-based Program Repair at Google

Multi-SWE-bench: A Multilingual Benchmark for Issue Resolving

Code to Think, Think to Code: A Survey on Code-Enhanced Reasoning and Reasoning-Driven Code Intelligence in LLMs

CodeCoR: An LLM-Based Self-Reflective Multi-Agent Framework for Code Generation

LeetCodeDataset: A Temporal Dataset for Robust Evaluation and Efficient Training of Code LLMs

Beyond Functional Correctness: Exploring Hallucinations in LLM-Generated Code

Human-AI Collaboration for Multi-Line Task Adjustment Using Local Large Language Models and a Digital Twin

FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance

CrossCodeEval: A Diverse and Multilingual Benchmark for Cross-File Code Completion

Can ChatGPT replace StackOverflow? A Study on Robustness and Reliability of Large Language Model Code Generation

Structured Chain-of-Thought Prompting for Code Generation

A New Era in Software Security: Towards Self-Healing Software via Large Language Models and Formal Verification

Large Language Models for Software Engineering: Survey and Open Problems

Impact of Code Language Models on Automated Program Repair