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)

301 to 360 of 1,389

Intent Formalization: A Grand Challenge for Reliable Coding in the Age of AI Agents
Shuvendu K. Lahiri
cs.SEcs.AIcs.PLarXiv:2603.17150v12026
RealSec-bench: A Benchmark for Evaluating Secure Code Generation in Real-World Repositories
Yanlin Wang, Ziyao Zhang, Chong Wang +5
cs.CRcs.SEarXiv:2601.22706v12026
DafnyPro: LLM-Assisted Automated Verification for Dafny Programs
Debangshu Banerjee, Olivier Bouissou, Stefan Zetzsche
cs.SEarXiv:2601.05385v12026
Programming by Chat: A Large-Scale Behavioral Analysis of 11,579 Real-World AI-Assisted IDE Sessions
Ningzhi Tang, Chaoran Chen, Zihan Fang +6
cs.SEcs.HCarXiv:2604.00436v22026
PlotChain: Deterministic Checkpointed Evaluation of Multimodal LLMs on Engineering Plot Reading
Mayank Ravishankara
cs.AIcs.SEarXiv:2602.13232v12026
6-Layer Model for a Structured Description and Categorization of Urban Traffic and Environment
Maike Scholtes, Lukas Westhofen, Lara Ruth Turner +11
cs.OHcs.AIcs.SEarXiv:2012.06319v22020
Edge Impulse: An MLOps Platform for Tiny Machine Learning
Shawn Hymel, Colby Banbury, Daniel Situnayake +13
cs.DCcs.LGcs.SEarXiv:2212.03332v32022
Where Do AI Coding Agents Fail? An Empirical Study of Failed Agentic Pull Requests in GitHub
Ramtin Ehsani, Sakshi Pathak, Shriya Rawal +3
cs.SEcs.AIarXiv:2601.15195v12026
Immersion in the GitHub Universe: Scaling Coding Agents to Mastery
Jiale Zhao, Guoxin Chen, Fanzhe Meng +11
cs.SEarXiv:2602.09892v42026
How does information access affect LLM monitors' ability to detect sabotage?
Rauno Arike, Raja Mehta Moreno, Rohan Subramani +2
cs.AIcs.SEarXiv:2601.21112v22026
What do we know about software development in startups?
Carmine Giardino, Michael Unterkalmsteiner, Nicolò Paternoster +2
cs.SEarXiv:2307.13707v12023
The History Is the Detector: Executing CVE Patch History, End-to-End
Qiushi Wu, Kevin Eykholt, Youngja Park +4
cs.CRcs.AIcs.SEarXiv:2609.05335v12026
Compressing Code Context for LLM-based Issue Resolution
Haoxiang Jia, Earl T. Barr, Sergey Mechtaev
cs.SEarXiv:2603.28119v12026
Goedel-Code-Prover: Hierarchical Proof Search for Open State-of-the-Art Code Verification
Zenan Li, Ziran Yang, Deyuan He +7
cs.SEcs.AIarXiv:2603.19329v32026
Evaluating and Improving Automated Repository-Level Rust Issue Resolution with LLM-based Agents
Jiahong Xiang, Wenxiao He, Xihua Wang +2
cs.SEarXiv:2602.22764v12026
ARIA - An Agentic Framework for Autonomous Testing of Infotainment Systems
António Azevedo, Bruno Lima, João Pascoal Faria
cs.SEcs.AIarXiv:2609.04913v12026
Better Understanding, Better Fixes? A Study of Hallucination in LLM-based Automated Program Repair
Xuemeng Cai, Jiakun Liu, Linhan Yang +2
cs.SEcs.AIarXiv:2609.04909v12026
ContractSkill: Repairable Contract-Based Skills for Multimodal Web Agents
Zijian Lu, Yiping Zuo, Yupeng Nie +4
cs.SEcs.AIarXiv:2603.20340v32026
Characterizing Faults in Agentic AI: A Taxonomy of Types, Symptoms, and Root Causes
Mehil B Shah, Mohammad Mehdi Morovati, Mohammad Masudur Rahman +1
cs.SEarXiv:2603.06847v22026
Beyond Code Generation: Reliability, Verification, and Cost Economics in the Agentic Software Development Lifecycle
Happy Bhati
cs.SEcs.AIarXiv:2609.04681v12026
In Line with Context: Repository-Level Code Generation via Context Inlining
Chao Hu, Wenhao Zeng, Yuling Shi +2
cs.SEcs.AIarXiv:2601.00376v32026
Dynamic Adaptation of the LLM Context for Generating Routines with Coupled Semantics
Gnaneswar Villuri, Hashmath Shaik, Alex Doboli
cs.SEcs.AIarXiv:2609.04570v12026
Building a research-software catalog with a coding agent: from hackathon prototype to public deployment
Kazuyoshi Yoshimi, Satoshi Terasaki, Gotai Yamada
cs.SEcs.AIcs.CYarXiv:2609.04711v12026
Advancing Requirements Engineering through Generative AI: Assessing the Role of LLMs
Chetan Arora, John Grundy, Mohamed Abdelrazek
cs.SEarXiv:2310.13976v22023
Software Development in Startup Companies: The Greenfield Startup Model
Carmine Giardino, Nicolò Paternoster, Michael Unterkalmsteiner +2
cs.SEarXiv:2308.09438v12023
Trace2Tower: Transition-Aware EigenTrace Induction of Multi-Level Skills for LLM Agents
Jiazheng Sun, Boyu Yang, Binhao Yuan +2
cs.AIcs.SEarXiv:2609.05261v12026
Cloud-OpsBench: A Reproducible Benchmark for Agentic Root Cause Analysis in Cloud Systems
Yilun Wang, Guangba Yu, Haiyu Huang +4
cs.SEarXiv:2603.00468v22026
SWE-ABS: Adversarial Benchmark Strengthening Exposes Inflated Success Rates on Test-based Benchmark
Boxi Yu, Yang Cao, Yuzhong Zhang +9
cs.SEarXiv:2603.00520v12026
Evaluating AGENTS.md: Are Repository-Level Context Files Helpful for Coding Agents?
Thibaud Gloaguen, Niels Mündler, Mark Müller +2
cs.SEcs.AIarXiv:2602.11988v22026
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
Is GitHub's Copilot as Bad as Humans at Introducing Vulnerabilities in Code?
Owura Asare, Meiyappan Nagappan, N. Asokan
cs.SEcs.CRarXiv:2204.04741v52022
Recommender System for Online Dating Service
Lukas Brozovsky, Vaclav Petricek
cs.IRcs.SEarXiv:cs/0703042v12007
AI IDEs or Autonomous Agents? Measuring the Impact of Coding Agents on Software Development
Shyam Agarwal, Hao He, Bogdan Vasilescu
cs.SEarXiv:2601.13597v22026
Deterministic LLM Inference Across GPU Kernels: Power-of-Two INT8 Quantization Scales and the Limits of Tolerance-Based Conformance
Teng-Ruei Chen
cs.LGcs.SEarXiv:2609.00363v12026
AgentWorm: Self-Propagating Attacks Across LLM Agent Ecosystems
Yihao Zhang, Zeming Wei, Xiaokun Luan +7
cs.CRcs.AIcs.LGarXiv:2603.15727v32026
Large Language Model for Vulnerability Detection: Emerging Results and Future Directions
Xin Zhou, Ting Zhang, David Lo
cs.SEarXiv:2401.15468v12024
The Web-CLI: Verifiable Privacy for Tools, Models, and Inference Engines in the Browser
Tejaswi Gowda
cs.HCcs.CRcs.SEarXiv:2608.28950v22026
SWE-Refactor: A Repository-Level Benchmark for Real-World LLM-Based Code Refactoring
Yisen Xu, Jinqiu Yang, Tse-Hsun +1
cs.SEarXiv:2602.03712v12026
The reach of a verification tool decides its value: A controlled study of verification surface, artifact quality, and cost in AI coding agents
Achint Mehta
cs.SEcs.AIarXiv:2608.28795v12026
Spec-Driven Development:From Code to Contract in the Age of AI Coding Assistants
Deepak Babu Piskala
cs.SEcs.AIarXiv:2602.00180v12026
Wink: Recovering from Misbehaviors in Coding Agents
Rahul Nanda, Chandra Maddila, Smriti Jha +3
cs.SEcs.AIcs.HCarXiv:2602.17037v22026
Large Language Models for Code Generation: A Comprehensive Survey of Challenges, Techniques, Evaluation, and Applications
Nam Huynh, Beiyu Lin
cs.SEcs.LGarXiv:2503.01245v22025
From Flat Logs to Causal Graphs: Hierarchical Failure Attribution for LLM-based Multi-Agent Systems
Yawen Wang, Wenjie Wu, Junjie Wang +1
cs.AIcs.SEarXiv:2602.23701v12026
Promises, Perils, and (Timely) Heuristics for Mining Coding Agent Activity
Romain Robbes, Théo Matricon, Thomas Degueule +2
cs.SEarXiv:2601.18345v12026
AICD Bench: A Challenging Benchmark for AI-Generated Code Detection
Daniil Orel, Dilshod Azizov, Indraneil Paul +3
cs.LGcs.SEarXiv:2602.02079v12026
Formal Scenario-Based Testing of Autonomous Vehicles: From Simulation to the Real World
Daniel J. Fremont, Edward Kim, Yash Vardhan Pant +7
eess.SYcs.LGcs.LOarXiv:2003.07739v22020
BenchGuard: Who Guards the Benchmarks? Automated Auditing of LLM Agent Benchmarks
Xinming Tu, Tianze Wang, Yingzhou +4
cs.CLcs.AIcs.SEarXiv:2604.24955v12026
Building the Truman Show: A TrustZone-Based Framework for Lightweight Out-of-band Kernel Security Monitoring
Zhenling Duan, Pan Dong, Renshuang Jiang +2
cs.CRcs.SEarXiv:2608.29758v12026
Cost-Effective Repository Exploration for Agentic Issue Localization
Mohammad Nour Al Awad, Sergey Ivanov
cs.SEcs.AIarXiv:2608.29675v12026
A Survey of Learning-based Automated Program Repair
Quanjun Zhang, Chunrong Fang, Yuxiang Ma +2
cs.SEarXiv:2301.03270v32023
Model Context Protocol Threat Modeling and Analyzing Vulnerabilities to Prompt Injection with Tool Poisoning
Charoes Huang, Xin Huang, Ngoc Phu Tran +1
cs.CRcs.SEarXiv:2603.22489v12026
From Technical Debt to Cognitive and Intent Debt: Rethinking Software Health in the Age of AI
Margaret-Anne Storey
cs.SEarXiv:2603.22106v42026
Debt Behind the AI Boom: A Large-Scale Empirical Study of AI-Generated Code in the Wild
Yue Liu, Ratnadira Widyasari, Yanjie Zhao +3
cs.SEarXiv:2603.28592v22026
Automatically Discovering, Reporting and Reproducing Android Application Crashes
Kevin Moran, Mario Linares-Vásquez, Carlos Bernal-Cárdenas +2
cs.SEarXiv:1706.01130v12017
Exploring Quantum Software Testing Across Research and Practice: Emerging Results from a Multivocal Literature Review
Rodolfo Gil-Pereira, Ronnie de Souza Santos, Cleyton Magalhaes +1
cs.SEarXiv:2609.00354v12026
Clawdrain: Exploiting Tool-Calling Chains for Stealthy Token Exhaustion in OpenClaw Agents
Ben Dong, Hui Feng, Qian Wang
cs.CRcs.SEarXiv:2603.00902v12026
Auditing Anonymous AI Models: A Four-Stage Protocol for Black-Box Identity Verification
Yisen Xi
cs.SEcs.AIcs.CRarXiv:2608.31142v12026
EffiSkill: Agent Skill Based Automated Code Efficiency Optimization
Zimu Wang, Yuling Shi, Mengfan Li +4
cs.SEcs.CLarXiv:2603.27850v12026
Evaluating Tiny Recursive Models Across Training for Code Generation
Anjani Sirivella, Aanisha Newaz, Glaucia Melo
cs.AIcs.LGcs.SEarXiv:2608.29376v12026
SkillProbe: Security Auditing for Emerging Agent Skill Marketplaces via Multi-Agent Collaboration
Zihan Guo, Zhiyu Chen, Xiaohang Nie +3
cs.CRcs.SEarXiv:2603.21019v12026

Software Engineering

Intent Formalization: A Grand Challenge for Reliable Coding in the Age of AI Agents

RealSec-bench: A Benchmark for Evaluating Secure Code Generation in Real-World Repositories

DafnyPro: LLM-Assisted Automated Verification for Dafny Programs

Programming by Chat: A Large-Scale Behavioral Analysis of 11,579 Real-World AI-Assisted IDE Sessions

PlotChain: Deterministic Checkpointed Evaluation of Multimodal LLMs on Engineering Plot Reading

6-Layer Model for a Structured Description and Categorization of Urban Traffic and Environment

Edge Impulse: An MLOps Platform for Tiny Machine Learning

Where Do AI Coding Agents Fail? An Empirical Study of Failed Agentic Pull Requests in GitHub

Immersion in the GitHub Universe: Scaling Coding Agents to Mastery

How does information access affect LLM monitors' ability to detect sabotage?

What do we know about software development in startups?

The History Is the Detector: Executing CVE Patch History, End-to-End

Compressing Code Context for LLM-based Issue Resolution

Goedel-Code-Prover: Hierarchical Proof Search for Open State-of-the-Art Code Verification

Evaluating and Improving Automated Repository-Level Rust Issue Resolution with LLM-based Agents

ARIA - An Agentic Framework for Autonomous Testing of Infotainment Systems

Better Understanding, Better Fixes? A Study of Hallucination in LLM-based Automated Program Repair

ContractSkill: Repairable Contract-Based Skills for Multimodal Web Agents

Characterizing Faults in Agentic AI: A Taxonomy of Types, Symptoms, and Root Causes

Beyond Code Generation: Reliability, Verification, and Cost Economics in the Agentic Software Development Lifecycle

In Line with Context: Repository-Level Code Generation via Context Inlining

Dynamic Adaptation of the LLM Context for Generating Routines with Coupled Semantics

Building a research-software catalog with a coding agent: from hackathon prototype to public deployment

Advancing Requirements Engineering through Generative AI: Assessing the Role of LLMs

Software Development in Startup Companies: The Greenfield Startup Model

Trace2Tower: Transition-Aware EigenTrace Induction of Multi-Level Skills for LLM Agents

Cloud-OpsBench: A Reproducible Benchmark for Agentic Root Cause Analysis in Cloud Systems

SWE-ABS: Adversarial Benchmark Strengthening Exposes Inflated Success Rates on Test-based Benchmark

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

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

Is GitHub's Copilot as Bad as Humans at Introducing Vulnerabilities in Code?

Recommender System for Online Dating Service

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

Deterministic LLM Inference Across GPU Kernels: Power-of-Two INT8 Quantization Scales and the Limits of Tolerance-Based Conformance

AgentWorm: Self-Propagating Attacks Across LLM Agent Ecosystems

Large Language Model for Vulnerability Detection: Emerging Results and Future Directions

The Web-CLI: Verifiable Privacy for Tools, Models, and Inference Engines in the Browser

SWE-Refactor: A Repository-Level Benchmark for Real-World LLM-Based Code Refactoring

The reach of a verification tool decides its value: A controlled study of verification surface, artifact quality, and cost in AI coding agents

Spec-Driven Development:From Code to Contract in the Age of AI Coding Assistants

Wink: Recovering from Misbehaviors in Coding Agents

Large Language Models for Code Generation: A Comprehensive Survey of Challenges, Techniques, Evaluation, and Applications

From Flat Logs to Causal Graphs: Hierarchical Failure Attribution for LLM-based Multi-Agent Systems

Promises, Perils, and (Timely) Heuristics for Mining Coding Agent Activity

AICD Bench: A Challenging Benchmark for AI-Generated Code Detection

Formal Scenario-Based Testing of Autonomous Vehicles: From Simulation to the Real World

BenchGuard: Who Guards the Benchmarks? Automated Auditing of LLM Agent Benchmarks

Building the Truman Show: A TrustZone-Based Framework for Lightweight Out-of-band Kernel Security Monitoring

Cost-Effective Repository Exploration for Agentic Issue Localization

A Survey of Learning-based Automated Program Repair

Model Context Protocol Threat Modeling and Analyzing Vulnerabilities to Prompt Injection with Tool Poisoning

From Technical Debt to Cognitive and Intent Debt: Rethinking Software Health in the Age of AI

Debt Behind the AI Boom: A Large-Scale Empirical Study of AI-Generated Code in the Wild

Automatically Discovering, Reporting and Reproducing Android Application Crashes

Exploring Quantum Software Testing Across Research and Practice: Emerging Results from a Multivocal Literature Review

Clawdrain: Exploiting Tool-Calling Chains for Stealthy Token Exhaustion in OpenClaw Agents

Auditing Anonymous AI Models: A Four-Stage Protocol for Black-Box Identity Verification

EffiSkill: Agent Skill Based Automated Code Efficiency Optimization

Evaluating Tiny Recursive Models Across Training for Code Generation

SkillProbe: Security Auditing for Emerging Agent Skill Marketplaces via Multi-Agent Collaboration