CUA-Sandbox: Efficient Environments for Computer-Use Agent Reinforcement Learning

arXiv:2609.32750 · cs.AI · Submitted 2026-09-26 · Read on arXiv

cs.AI

Submitted: 2026-09-26

Updated: 2026-09-26

Terminology

• Benchmark — 22× in this paper · explained in 2 episodes
• Ablation — 14× in this paper · explained in 1 episode
• Reinforcement Learning — 9× in this paper · explained in 4 episodes
• Fidelity — 5× in this paper · explained in 2 episodes
• Benchmarking — 4× in this paper · explained in 3 episodes
• State Management — 4× in this paper · explained in 3 episodes
• World Model — 4× in this paper · explained in 7 episodes
• Consistency — 2× in this paper · explained in 3 episodes
• Core — 2× in this paper · explained in 2 episodes
• Fine-Tuning — 2× in this paper · explained in 5 episodes
• Grounding — 2× in this paper · explained in 3 episodes
• Verifier — 2× in this paper · explained in 2 episodes
• AI Agents — 1× in this paper · explained in 2 episodes
• Ablation study — 1× in this paper · explained in 1 episode
• Reinforcement Learning (RL) — 1× in this paper · explained in 25 episodes
• Reward Function — 1× in this paper · explained in 2 episodes
• Sim-to-Real Gap — 1× in this paper · explained in 6 episodes
• Supervised Fine-Tuning (SFT) — 1× in this paper · explained in 8 episodes
• Verifiable Rewards — 1× in this paper · explained in 2 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• Gym-Anything: Turn any Software into an Agent Environment
• ClawGym: A Scalable Framework for Building Effective Claw 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
• Scaling Agent Learning via Experience Synthesis
• SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents
• Mind2Web: Towards a Generalist Agent for the Web
• Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence
• WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks?
• The Rollout Infrastructure Tax in Coding-Agent Reinforcement Learning
• WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models
• SearchEyes: Towards Frontier Multimodal Deep Search Intelligence via Search World Simulation
• VisualWebArena: Evaluating Multimodal Agents on Realistic Visual Web Tasks
• Qwen-CUA: Native Computer Use for (almost) Everything
• WEBSERV: A Full-Stack and RL-Ready Web Environment for Training Web Agents at Scale
• Orchard: An Open-Source Agentic Modeling Framework
• UI-TARS: Pioneering Automated GUI Interaction with Native Agents
• AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents
• AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agents
• ScaleEnv: Scaling Environment Synthesis from Scratch for Generalist Interactive Tool-Use Agent Training

Related papers

• 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
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection