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

P
Proofpoint News Feed
Martin Fowler
Martin Fowler
The GitHub Blog
The GitHub Blog
B
Blog RSS Feed
U
Unit 42
阮一峰的网络日志
阮一峰的网络日志
量子位
GbyAI
GbyAI
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
云风的 BLOG
云风的 BLOG
小众软件
小众软件
博客园 - 三生石上(FineUI控件)
L
LangChain Blog
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
博客园_首页
IT之家
IT之家
V
Visual Studio Blog
Y
Y Combinator Blog
Blog — PlanetScale
Blog — PlanetScale
宝玉的分享
宝玉的分享
Apple Machine Learning Research
Apple Machine Learning Research
I
InfoQ
D
Docker
V
V2EX

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
The Shift from Writing to Pruning Software: A Bonsai-Insp...
Raula Gaikovina Kula, Christoph Treude · 2025-03-05 · via cs.SE updates on arXiv.org

The rise of AI-driven coding assistants signals a fundamental shift in how software is built. While AI coding assistants have been integrated into existing Integrated Development Environments (IDEs), their full potential remains largely untapped. A key challenge is that these AI assistants can suffer from hallucinations, leading developers down decision paths that the AI should not dictate, sometimes even without the users awareness or consent. Moreover, current static-file IDEs lack the mechanisms to address critical issues such as tracking the provenance of AI-generated code and integrating version control in a way that aligns with the dynamic nature of AI-assisted development. As a result, developers are left without the necessary tools to manage, refine, and validate AI generated code systematically, making it difficult to ensure correctness, maintainability, and trust in the development process. Existing IDEs treat AI-generated code as static text, offering limited support for managing its evolution, refinement, or multiple alternative paths. Drawing inspiration from the ancient art of Japanese Bonsai gardening focused on balance, structure, and deliberate pruning: we propose a new approach to IDEs, where AI is allowed to generate in its true, unconstrained form, free from traditional file structures. This approach fosters a more fluid and interactive method for code evolution. We introduce the concept of a Bonsai-inspired IDE, structured as a graph of generated code snippets and multiple code paths, enabling developers to reshape AI generated code to suit their needs. Our vision calls for a shift away from a static file based model toward a dynamic, evolving system that allows for continuous refinement of generated code, with the IDE evolving alongside AI powered modifications rather than merely serving as a place to write and edit code.