惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

大猫的无限游戏
大猫的无限游戏
aimingoo的专栏
aimingoo的专栏
I
InfoQ
B
Blog RSS Feed
D
DataBreaches.Net
S
SegmentFault 最新的问题
P
Proofpoint News Feed
A
About on SuperTechFans
WordPress大学
WordPress大学
Hugging Face - Blog
Hugging Face - Blog
博客园 - 司徒正美
小众软件
小众软件
博客园 - Franky
有赞技术团队
有赞技术团队
D
Docker
T
Tailwind CSS Blog
雷峰网
雷峰网
让小产品的独立变现更简单 - ezindie.com
让小产品的独立变现更简单 - ezindie.com
Blog — PlanetScale
Blog — PlanetScale
酷 壳 – CoolShell
酷 壳 – CoolShell
B
Blog
V
Visual Studio Blog
宝玉的分享
宝玉的分享
爱范儿
爱范儿

cs.SE updates on arXiv.org

VLA Foundry: A Unified Framework for Training Vision-Language-Action Models Evaluating LLM-Generated Obfuscated XSS Payloads for Machine Learning-Based Detection Do Agents Dream of Root Shells? Partial-Credit Evaluation of LLM Agents in Capture the Flag Challenges Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery From Particles to Perils: SVGD-Based Hazardous Scenario Generation for Autonomous Driving Systems Testing Choose Your Own Adventure: Non-Linear AI-Assisted Programming with EvoGraph Human-Machine Co-Boosted Bug Report Identification with Mutualistic Neural Active Learning LLMSniffer: Detecting LLM-Generated Code via GraphCodeBERT and Supervised Contrastive Learning Neurosymbolic Repo-level Code Localization CodeMMR: Bridging Natural Language, Code, and Image for Unified Retrieval Symbolic Guardrails for Domain-Specific Agents: Stronger Safety and Security Guarantees Without Sacrificing Utility Verification Modulo Tested Library Contracts The Semi-Executable Stack: Agentic Software Engineering and the Expanding Scope of SE Scaling Test-Time Compute for Agentic Coding AI-Assisted Requirements Engineering: An Empirical Evaluation Relative to Expert Judgment From Procedural Skills to Strategy Genes: Towards Experience-Driven Test-Time Evolution Atropos: Improving Cost-Benefit Trade-off of LLM-based Agents under Self-Consistency with Early Termination and Model Hotswap Vibe-Coding: Feedback-Based Automated Verification with no Human Code Inspection, a Feasibility Study Benchmarks for Trajectory Safety Evaluation and Diagnosis in OpenClaw and Codex: ATBench-Claw and ATBench-Codex Bounded Autonomy for Enterprise AI: Typed Action Contracts and Consumer-Side Execution AIPC: Agent-Based Automation for AI Model Deployment with Qualcomm AI Runtime Analyzing Chain of Thought (CoT) Approaches in Control Flow Code Deobfuscation Tasks Asking What Matters: Reward-Driven Clarification for Software Engineering Tasks Prompt-Driven Code Summarization: A Systematic Literature Review LinuxArena: A Control Setting for AI Agents in Live Production Software Environments LLMs taking shortcuts in test generation: A study with SAP HANA and LevelDB Large Language Models to Enhance Business Process Modeling: Past, Present, and Future Trends CollabCoder: Plan-Code Co-Evolution via Collaborative Decision-Making for Efficient Code Generation Sentiment analysis for software engineering: How far can zero-shot learning (ZSL) go? Learning from Change: Predictive Models for Incident Prevention in a Regulated IT Environment
An Empirical Study of Generative AI Adoption in Software ...
Görkem Giray, Onur Demirörs, Marcos Kalinowski, Daniel Mendez · 2025-12-29 · via cs.SE updates on arXiv.org

Context. GenAI tools are being increasingly adopted by practitioners in SE, promising support for several SE activities. Despite increasing adoption, we still lack empirical evidence on how GenAI is used in practice, the benefits it provides, the challenges it introduces, and its broader organizational and societal implications. Objective. This study aims to provide an overview of the status of GenAI adoption in SE. It investigates the status of GenAI adoption, associated benefits and challenges, institutionalization of tools and techniques, and anticipated long term impacts on SE professionals and the community. Results. The results indicate a wide adoption of GenAI tools and how they are deeply integrated into daily SE work, particularly for implementation, verification and validation, personal assistance, and maintenance-related tasks. Practitioners report substantial benefits, most notably reduction in cycle time, quality improvements, enhanced support in knowledge work, and productivity gains. However, objective measurement of productivity and quality remains limited in practice. Significant challenges persist, including incorrect or unreliable outputs, prompt engineering difficulties, validation overhead, security and privacy concerns, and risks of overreliance. Institutionalization of tools and techniques seems to be common, but it varies considerably, with a strong focus on tool access and less emphasis on training and governance. Practitioners expect GenAI to redefine rather than replace their roles, while expressing moderate concern about job market contraction and skill shifts.