Catalyzing Interactive HTML Generation Capabilities via High-Fidelity Reinforcement Learning
cs.AI
Submitted: 2026-11-03
Updated: 2026-11-03
Code: https://github.com/microsoft/playwright
Terminology
Sources
- pix2code: Generating Code from a Graphical User Interface Screenshot
- WebGrader: Training LLMs for Web Development with Self-Evolving Programmatic Grader
- VisRefiner: Learning from Visual Differences for Screenshot-to-Code Generation
- GUI Agents for Continual Game Generation
- WebGen-R1: Incentivizing Large Language Models to Generate Functional and Aesthetic Websites with Reinforcement Learning
- Design the Feedback, Not Just the Reward: Environments for Open-Ended Reinforcement Learning
- Execution-Grounded Credit Assignment for GRPO in Code Generation
- WebRenderBench: Enhancing Web Interface Generation through Layout-Style Consistency and Reinforcement Learning
- Unlocking the conversion of Web Screenshots into HTML Code with the WebSight Dataset
- PlayCoder: Making LLM-Generated GUI Code Playable
- UI-TARS: Pioneering Automated GUI Interaction with Native Agents
- Proximal Policy Optimization Algorithms
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism
- HTMLCure: Turning Browser Experience into State Guided Repair for Interactive HTML
- Cookie-Bench: Continuous On-screen Key Interaction Evaluation for Web Generation
- ArtifactsBench: Bridging the Visual-Interactive Gap in LLM Code Generation Evaluation
- WebGameBench: Requirement-to-Application Evaluation for Coding Agents via Browser-Native Games
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents