CUA-Master: Scaling Computer-use Agents through Open-World Recursive Improvements
cs.AI
Submitted: 2026-11-02
Updated: 2026-11-02
Terminology
Sources
- cua-speedrun: Standardized Benchmarking of the Speed of Computer-Use Agents
- Windows Agent Arena: Evaluating Multi-Modal OS Agents at Scale
- GUI-GENESIS: Automated Synthesis of Efficient Environments with Verifiable Rewards for GUI Agent Post-Training
- HybridCUA: Learning to Orchestrate GUI and CLI for Computer-Use Agents
- RL Starts before RL: On Policy Distillation for Better Reinforcement Learning
- MacAgentBench: Benchmarking AI Agents on Real-World macOS Desktop
- ToolCUA: Towards Optimal GUI-Tool Path Orchestration for Computer Use Agents
- EvoCUA-1.5: Online Reinforcement Learning for Multi-turn Computer-Use Agents
- CUA-Suite: Massive Human-annotated Video Demonstrations for Computer-Use Agents
- ProCUA-SFT Technical Report
- WeaveBench: A Long-Horizon, Real-World Benchmark for Computer-Use Agents with Hybrid Interfaces
- Qwen-CUA: Native Computer Use for (almost) Everything
- SCALECUA: Scaling Computer Use Agents with Verifiable Task Synthesis and Efficient Online RL
- UI-TARS: Pioneering Automated GUI Interaction with Native Agents
- CUA-Universe: A Scalable and Dynamic Environment for Hybrid GUI+CLI Agents
- Agents' Last Exam
- Kimi K3: Open Frontier Intelligence
- UI-Venus-2 Technical Report
- CUA-Gym: Scaling Verifiable Training Environments and Tasks for Computer-Use Agents
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