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

Engineering at Meta
Engineering at Meta
博客园_首页
J
Java Code Geeks
Jina AI
Jina AI
B
Blog RSS Feed
量子位
有赞技术团队
有赞技术团队
M
MIT News - Artificial intelligence
L
LangChain Blog
Microsoft Security Blog
Microsoft Security Blog
小众软件
小众软件
博客园 - 聂微东
月光博客
月光博客
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 - 三生石上(FineUI控件)
Last Week in AI
Last Week in AI
MongoDB | Blog
MongoDB | Blog
I
InfoQ
罗磊的独立博客
H
Hackread – Cybersecurity News, Data Breaches, AI and More
爱范儿
爱范儿
Y
Y Combinator Blog
Vercel News
Vercel News
雷峰网
雷峰网

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
Prodirect Manipulation: Bidirectional Programming for the...
Ravi Chugh · 2015-10-23 · via cs.SE updates on arXiv.org

Software interfaces today generally fall at either end of a spectrum. On one end are programmable systems, which allow expert users (i.e. programmers) to write software artifacts that describe complex abstractions, but programs are disconnected from their eventual output. On the other end are domain-specific graphical user interfaces (GUIs), which allow end users (i.e. non-programmers) to easily create varied content but present insurmountable walls when a desired feature is not built-in. Both programmatic and direct manipulation have distinct strengths, but users must typically choose one over the other or use some ad-hoc combination of systems. Our goal, put simply, is to bridge this divide. We envision novel software systems that tightly couple programmatic and direct manipulation --- a combination we dub prodirect manipulation --- for a variety of use cases. This will require advances in a broad range of software engineering disciplines, from program analysis and program synthesis technology to user interface design and evaluation. In this extended abstract, we propose two general strategies --- real-time program synthesis and domain-specific synthesis of general-purpose programs --- that may prove fruitful for overcoming the technical challenges. We also discuss metrics that will be important in evaluating the usability and utility of prodirect manipulation systems.