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)

1,141 to 1,200 of 1,389

MEnvAgent: Scalable Polyglot Environment Construction for Verifiable Software Engineering
Chuanzhe Guo, Jingjing Wu, Sijun He +10
cs.SEcs.AIarXiv:2601.22859v32026
AutoSaddler: Automatic Harness Optimization with Durable Updates from Agent Execution Traces
Sungho Park, Wonjoong Kim, Rongyuan Tan +10
cs.AIcs.CLcs.LGarXiv:2608.23041v12026
Formalizing and Automating Fine-Grained Move Refactorings Across Methods
Kota Yasuhara, Shinpei Hayashi
cs.SEarXiv:2608.23377v12026
Execution-Anchored Hallucination Calibration Reranking for Verilog Code Generation
Guang Yang, Xing Hu, Xiang Chen +2
cs.SEcs.ARarXiv:2608.22938v12026
DIVE: Scaling Diversity in Agentic Task Synthesis for Generalizable Tool Use
Aili Chen, Chi Zhang, Junteng Liu +11
cs.AIcs.SEarXiv:2603.11076v12026
An Empirical Study of the TianoCore Community
Nazanin Siavash, Connor Glosner, Ayushi Sharma +4
cs.SEarXiv:2608.23280v12026
IQuest-Coder-V1 Technical Report
Jian Yang, Wei Zhang, Shawn Guo +35
cs.AIcs.CLcs.SEarXiv:2603.16733v12026
ContractFuzzer: Fuzzing Smart Contracts for Vulnerability Detection
Bo Jiang, Ye Liu, W. K. Chan
cs.SEcs.CRarXiv:1807.03932v22018
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
Prompt Injection attack against LLM-integrated Applications
Yi Liu, Gelei Deng, Yuekang Li +9
cs.CRcs.AIcs.CLarXiv:2306.05499v32023
Repo2Skill-Evo: Repository Skills Go Stale in Silence
Chenyuan Duan, Ge Shi, Zineng Mao +10
cs.AIcs.SEarXiv:2608.21964v12026
graph2vec: Learning Distributed Representations of Graphs
Annamalai Narayanan, Mahinthan Chandramohan, Rajasekar Venkatesan +3
cs.AIcs.CLcs.CRarXiv:1707.05005v12017
On Randomness in Agentic Evals
Bjarni Haukur Bjarnason, André Silva, Martin Monperrus
cs.LGcs.AIcs.SEarXiv:2602.07150v32026
GameDevBench: Evaluating Agentic Capabilities Through Game Development
Wayne Chi, Yixiong Fang, Arnav Yayavaram +8
cs.AIcs.CLcs.SEarXiv:2602.11103v22026
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
Guidelines to Prompt Large Language Models for Code Generation: An Empirical Characterization
Alessandro Midolo, Alessandro Giagnorio, Fiorella Zampetti +3
cs.SEarXiv:2601.13118v12026
ToolPRMBench: Evaluating and Advancing Process Reward Models for Tool-using Agents
Dawei Li, Yuguang Yao, Zhen Tan +2
cs.AIcs.SEarXiv:2601.12294v12026
Advances and Frontiers of LLM-based Issue Resolution in Software Engineering: A Comprehensive Survey
Caihua Li, Lianghong Guo, Yanlin Wang +9
cs.SEcs.CLarXiv:2601.11655v12026
AACR-Bench: Evaluating Automatic Code Review with Holistic Repository-Level Context
Lei Zhang, Yongda Yu, Minghui Yu +11
cs.SEcs.AIarXiv:2601.19494v32026
ReflexiCoder: Teaching Large Language Models to Self-Reflect on Generated Code and Self-Correct It via Reinforcement Learning
Juyong Jiang, Jiasi Shen, Sunghun Kim +3
cs.CLcs.LGcs.SEarXiv:2603.05863v22026
ASA: Backbone-Training-Free Representation Engineering for Tool-Calling Agents
Youjin Wang, Run Zhou, Yingjie Ma +6
cs.SEcs.AIarXiv:2602.04935v32026
Composable Trust Infrastructure for Manufacturing Knowledge Graphs: Cross-System Provenance, Temporal Reasoning, and Decision Traceability
Grama Chethan
cs.AIcs.SEarXiv:2608.21418v12026
Confident and Wrong: Silent Semantic Failures in Coding Agents
Aman Mehta
cs.SEcs.AIarXiv:2603.25764v32026
InCoder-32B: Code Foundation Model for Industrial Scenarios
Jian Yang, Wei Zhang, Jiajun Wu +25
cs.SEcs.AIarXiv:2603.16790v32026
Machine Learning Testing: Survey, Landscapes and Horizons
Jie M. Zhang, Mark Harman, Lei Ma +1
cs.LGcs.AIcs.SEarXiv:1906.10742v22019
KAPSO: A Knowledge-grounded framework for Autonomous Program Synthesis and Optimization
Alireza Nadafian, Alireza Mohammadshahi, Majid Yazdani
cs.AIcs.CLcs.SEarXiv:2601.21526v22026
A Comprehensive Survey on Fog Computing: State-of-the-art and Research Challenges
Carla Mouradian, Diala Naboulsi, Sami Yangui +3
cs.DCcs.SEarXiv:1710.11001v32017
MegaFlow: Large-Scale Distributed Orchestration System for the Agentic Era
Lei Zhang, Mouxiang Chen, Ruisheng Cao +16
cs.DCcs.SEarXiv:2601.07526v22026
Prime Agent: A Self-Improving RLM Harness
Seth Karten, Alex L. Zhang, Kevin Thomas +8
cs.AIcs.CLcs.SEarXiv:2608.23552v12026
Test-Driven AI Agent Definition (TDAD): Compiling Tool-Using Agents from Behavioral Specifications
Tzafrir Rehan
cs.SEcs.AIarXiv:2603.08806v12026
Rethinking the Value of Agent-Generated Tests for LLM-Based Software Engineering Agents
Zhi Chen, Zhensu Sun, Yuling Shi +4
cs.SEcs.AIarXiv:2602.07900v22026
InCoder: A Generative Model for Code Infilling and Synthesis
Daniel Fried, Armen Aghajanyan, Jessy Lin +7
cs.SEcs.CLcs.LGarXiv:2204.05999v32022
CodeBLEU: a Method for Automatic Evaluation of Code Synthesis
Shuo Ren, Daya Guo, Shuai Lu +7
cs.SEcs.CLarXiv:2009.10297v22020
SWE-Universe: Scale Real-World Verifiable Environments to Millions
Mouxiang Chen, Lei Zhang, Yunlong Feng +15
cs.SEcs.AIarXiv:2602.02361v12026
Learning to Represent Programs with Graphs
Miltiadis Allamanis, Marc Brockschmidt, Mahmoud Khademi
cs.LGcs.AIcs.PLarXiv:1711.00740v32017
OpenHands: An Open Platform for AI Software Developers as Generalist Agents
Xingyao Wang, Boxuan Li, Yufan Song +21
cs.SEcs.AIcs.CLarXiv:2407.16741v32024
Agentic Code Reasoning
Shubham Ugare, Satish Chandra
cs.SEcs.AIcs.PLarXiv:2603.01896v22026
Computer-Using World Model
Yiming Guan, Rui Yu, John Zhang +15
cs.SEarXiv:2602.17365v12026
Terminal Agents Suffice for Enterprise Automation
Patrice Bechard, Orlando Marquez Ayala, Emily Chen +5
cs.SEcs.AIcs.CLarXiv:2604.00073v32026
Vision2Web: A Hierarchical Benchmark for Visual Website Development with Agent Verification
Zehai He, Wenyi Hong, Zhen Yang +4
cs.SEcs.AIarXiv:2603.26648v32026
Slither: A Static Analysis Framework For Smart Contracts
Josselin Feist, Gustavo Grieco, Alex Groce
cs.SEcs.CRarXiv:1908.09878v12019
An Overview on Smart Contracts: Challenges, Advances and Platforms
Zibin Zheng, Shaoan Xie, Hong-Ning Dai +4
cs.SEcs.DCarXiv:1912.10370v12019
Human-AI Synergy in Agentic Code Review
Suzhen Zhong, Shayan Noei, Ying Zou +1
cs.SEarXiv:2603.15911v12026
daVinci-Dev: Agent-native Mid-training for Software Engineering
Ji Zeng, Dayuan Fu, Tiantian Mi +14
cs.SEcs.AIarXiv:2601.18418v22026
Blockchain for Internet of Things: A Survey
Hong-Ning Dai, Zibin Zheng, Yan Zhang
cs.NIcs.DCcs.SEarXiv:1906.00245v52019
Questioning the AI: Informing Design Practices for Explainable AI User Experiences
Q. Vera Liao, Daniel Gruen, Sarah Miller
cs.HCcs.AIcs.LGarXiv:2001.02478v32020
Spike-Killer: Evidence-Gated LLM Assistance for Safe Performance Diagnosis on a Real Windows Workstation
Baocheng Zeng, Jinhao Yang
cs.SEarXiv:2608.21069v12026
Toward Understanding Operating System Defects
Hongyao Zuo, Jiali Li, Jiajun Jiang
cs.SEarXiv:2608.20643v12026
An Extensive Empirical Study on Code Translation Technique
Ruihang Fan, Jiajun Jiang, Xinpeng Wang +3
cs.SEcs.PLarXiv:2608.20776v12026
BeyondSWE: Can Current Code Agent Survive Beyond Single-Repo Bug Fixing?
Guoxin Chen, Fanzhe Meng, Jiale Zhao +12
cs.CLcs.SEarXiv:2603.03194v22026
SERA: Soft-Verified Efficient Repository Agents
Ethan Shen, Daniel Tormoen, Saurabh Shah +2
cs.CLcs.LGcs.SEarXiv:2601.20789v32026
Benchmarking Reward Hack Detection in Code Environments via Contrastive Analysis
Darshan Deshpande, Anand Kannappan, Rebecca Qian
cs.SEcs.AIcs.LGarXiv:2601.20103v12026
The Substitution Escrow Threshold: When "Compatible With" Becomes Safe Enough to Buy
Amadeus Brandes
cs.SEcs.CYarXiv:2608.21221v12026
SWE-Master: Unleashing the Potential of Software Engineering Agents via Post-Training
Huatong Song, Lisheng Huang, Shuang Sun +11
cs.SEcs.CLarXiv:2602.03411v22026
An introduction to Docker for reproducible research, with examples from the R environment
Carl Boettiger
cs.SEarXiv:1410.0846v12014
SWE-rebench V2: Language-Agnostic SWE Task Collection at Scale
Ibragim Badertdinov, Maksim Nekrashevich, Anton Shevtsov +1
cs.SEcs.CLarXiv:2602.23866v22026
Beyond Fault Localization: A Trajectory-Level Study of LLM Agents for Microservice Root Cause Analysis
Qisheng Lu, Aoyang Fang, Junjielong Xu +5
cs.SEarXiv:2608.21310v12026
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
AutoWebWorld: Synthesizing Infinite Verifiable Web Environments via Finite State Machines
Yifan Wu, Yiran Peng, Yiyu Chen +12
cs.AIcs.SEarXiv:2602.14296v12026
SWE-World: Building Software Engineering Agents in Docker-Free Environments
Shuang Sun, Huatong Song, Lisheng Huang +11
cs.SEcs.CLarXiv:2602.03419v12026

Software Engineering

MEnvAgent: Scalable Polyglot Environment Construction for Verifiable Software Engineering

AutoSaddler: Automatic Harness Optimization with Durable Updates from Agent Execution Traces

Formalizing and Automating Fine-Grained Move Refactorings Across Methods

Execution-Anchored Hallucination Calibration Reranking for Verilog Code Generation

DIVE: Scaling Diversity in Agentic Task Synthesis for Generalizable Tool Use

An Empirical Study of the TianoCore Community

IQuest-Coder-V1 Technical Report

ContractFuzzer: Fuzzing Smart Contracts for Vulnerability Detection

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

Prompt Injection attack against LLM-integrated Applications

Repo2Skill-Evo: Repository Skills Go Stale in Silence

graph2vec: Learning Distributed Representations of Graphs

On Randomness in Agentic Evals

GameDevBench: Evaluating Agentic Capabilities Through Game Development

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

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

ToolPRMBench: Evaluating and Advancing Process Reward Models for Tool-using Agents

Advances and Frontiers of LLM-based Issue Resolution in Software Engineering: A Comprehensive Survey

AACR-Bench: Evaluating Automatic Code Review with Holistic Repository-Level Context

ReflexiCoder: Teaching Large Language Models to Self-Reflect on Generated Code and Self-Correct It via Reinforcement Learning

ASA: Backbone-Training-Free Representation Engineering for Tool-Calling Agents

Composable Trust Infrastructure for Manufacturing Knowledge Graphs: Cross-System Provenance, Temporal Reasoning, and Decision Traceability

Confident and Wrong: Silent Semantic Failures in Coding Agents

InCoder-32B: Code Foundation Model for Industrial Scenarios

Machine Learning Testing: Survey, Landscapes and Horizons

KAPSO: A Knowledge-grounded framework for Autonomous Program Synthesis and Optimization

A Comprehensive Survey on Fog Computing: State-of-the-art and Research Challenges

MegaFlow: Large-Scale Distributed Orchestration System for the Agentic Era

Prime Agent: A Self-Improving RLM Harness

Test-Driven AI Agent Definition (TDAD): Compiling Tool-Using Agents from Behavioral Specifications

Rethinking the Value of Agent-Generated Tests for LLM-Based Software Engineering Agents

InCoder: A Generative Model for Code Infilling and Synthesis

CodeBLEU: a Method for Automatic Evaluation of Code Synthesis

SWE-Universe: Scale Real-World Verifiable Environments to Millions

Learning to Represent Programs with Graphs

OpenHands: An Open Platform for AI Software Developers as Generalist Agents

Agentic Code Reasoning

Computer-Using World Model

Terminal Agents Suffice for Enterprise Automation

Vision2Web: A Hierarchical Benchmark for Visual Website Development with Agent Verification

Slither: A Static Analysis Framework For Smart Contracts

An Overview on Smart Contracts: Challenges, Advances and Platforms

Human-AI Synergy in Agentic Code Review

daVinci-Dev: Agent-native Mid-training for Software Engineering

Blockchain for Internet of Things: A Survey

Questioning the AI: Informing Design Practices for Explainable AI User Experiences

Spike-Killer: Evidence-Gated LLM Assistance for Safe Performance Diagnosis on a Real Windows Workstation

Toward Understanding Operating System Defects

An Extensive Empirical Study on Code Translation Technique

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

SERA: Soft-Verified Efficient Repository Agents

Benchmarking Reward Hack Detection in Code Environments via Contrastive Analysis

The Substitution Escrow Threshold: When "Compatible With" Becomes Safe Enough to Buy

SWE-Master: Unleashing the Potential of Software Engineering Agents via Post-Training

An introduction to Docker for reproducible research, with examples from the R environment

SWE-rebench V2: Language-Agnostic SWE Task Collection at Scale

Beyond Fault Localization: A Trajectory-Level Study of LLM Agents for Microservice Root Cause Analysis

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

AutoWebWorld: Synthesizing Infinite Verifiable Web Environments via Finite State Machines

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