Copertina

CUA-Gym: Scaling Verifiable Training Environments and Tasks for Computer-Use Agents

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Wang, Bowen, Lu, Dunjie, Wang, Junli, Bai, Tianyi, Liu, Shixuan, Zhang, Zhipeng, Wang, Haiquan, Hu, Hao, Xie, Tianbao, Bai, Shuai, Liu, Dayiheng, Shen, Que, Lin, Junyang, Yu, Tao
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Artificial Intelligence Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

OpenCUA: Open Foundations for Computer-Use Agents
di: Wang, Xinyuan, et al.
Pubblicazione: (2025)

ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data
di: Liu, Zhaoyang, et al.
Pubblicazione: (2025)

WebGym: Scaling Training Environments for Visual Web Agents with Realistic Tasks
di: Bai, Hao, et al.
Pubblicazione: (2026)

PRO-CUA: Process-Reward Optimization for Computer Use Agents
di: He, Yifei, et al.
Pubblicazione: (2026)

Training Software Engineering Agents and Verifiers with SWE-Gym
di: Pan, Jiayi, et al.
Pubblicazione: (2024)

VideoAgentTrek: Computer Use Pretraining from Unlabeled Videos
di: Lu, Dunjie, et al.
Pubblicazione: (2025)

Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction
di: Xu, Yiheng, et al.
Pubblicazione: (2024)

CUA-Skill: Develop Skills for Computer Using Agent
di: Chen, Tianyi, et al.
Pubblicazione: (2026)

LiteCUA: Computer as MCP Server for Computer-Use Agent on AIOS
di: Mei, Kai, et al.
Pubblicazione: (2025)

RedTeamCUA: Realistic Adversarial Testing of Computer-Use Agents in Hybrid Web-OS Environments
di: Liao, Zeyi, et al.
Pubblicazione: (2025)

Hybrid-Gym: Training Coding Agents to Generalize Across Tasks
di: Xie, Yiqing, et al.
Pubblicazione: (2026)

TreeCUA: Efficiently Scaling GUI Automation with Tree-Structured Verifiable Evolution
di: Jiang, Deyang, et al.
Pubblicazione: (2026)

EvoCUA: Evolving Computer Use Agents via Learning from Scalable Synthetic Experience
di: Xue, Taofeng, et al.
Pubblicazione: (2026)

CUA-Suite: Massive Human-annotated Video Demonstrations for Computer-Use Agents
di: Jian, Xiangru, et al.
Pubblicazione: (2026)

UltraCUA: A Foundation Model for Computer Use Agents with Hybrid Action
di: Yang, Yuhao, et al.
Pubblicazione: (2025)

SWE-Universe: Scale Real-World Verifiable Environments to Millions
di: Chen, Mouxiang, et al.
Pubblicazione: (2026)

HistoGym: A Reinforcement Learning Environment for Histopathological Image Analysis
di: Liu, Zhi-Bo, et al.
Pubblicazione: (2024)

AgentTrek: Agent Trajectory Synthesis via Guiding Replay with Web Tutorials
di: Xu, Yiheng, et al.
Pubblicazione: (2024)

ToolCUA: Towards Optimal GUI-Tool Path Orchestration for Computer Use Agents
di: Hu, Xuhao, et al.
Pubblicazione: (2026)

A11y-CUA Dataset: Characterizing the Accessibility Gap in Computer Use Agents
di: Mohanbabu, Ananya Gubbi, et al.
Pubblicazione: (2026)

R2E-Gym: Procedural Environments and Hybrid Verifiers for Scaling Open-Weights SWE Agents
di: Jain, Naman, et al.
Pubblicazione: (2025)

IntentCUA: Learning Intent-level Representations for Skill Abstraction and Multi-Agent Planning in Computer-Use Agents
di: Lee, Seoyoung, et al.
Pubblicazione: (2026)

UserBench: An Interactive Gym Environment for User-Centric Agents
di: Qian, Cheng, et al.
Pubblicazione: (2025)

Think, Then Verify: A Hypothesis-Verification Multi-Agent Framework for Long Video Understanding
di: Wang, Zheng, et al.
Pubblicazione: (2026)

MedAgentGym: A Scalable Agentic Training Environment for Code-Centric Reasoning in Biomedical Data Science
di: Xu, Ran, et al.
Pubblicazione: (2025)

Scaling Computer-Use Grounding via User Interface Decomposition and Synthesis
di: Xie, Tianbao, et al.
Pubblicazione: (2025)

Soft Adaptive Policy Optimization
di: Gao, Chang, et al.
Pubblicazione: (2025)

VisGym: Diverse, Customizable, Scalable Environments for Multimodal Agents
di: Wang, Zirui, et al.
Pubblicazione: (2026)

WebWorld: A Large-Scale World Model for Web Agent Training
di: Xiao, Zikai, et al.
Pubblicazione: (2026)

CLI-Gym: Scalable CLI Task Generation via Agentic Environment Inversion
di: Lin, Yusong, et al.
Pubblicazione: (2026)

OceanGym: A Benchmark Environment for Underwater Embodied Agents
di: Xue, Yida, et al.
Pubblicazione: (2025)

Efficient Agent Training for Computer Use
di: He, Yanheng, et al.
Pubblicazione: (2025)

Scaling Agents for Computer Use
di: Gonzalez-Pumariega, Gonzalo, et al.
Pubblicazione: (2025)

AExGym: Benchmarks and Environments for Adaptive Experimentation
di: Wang, Jimmy, et al.
Pubblicazione: (2024)

D3-Gym: Constructing Real-World Verifiable Environments for Data-Driven Discovery
di: Moussa, Hanane Nour, et al.
Pubblicazione: (2026)

Parallel Scaling Law for Language Models
di: Chen, Mouxiang, et al.
Pubblicazione: (2025)

TRACER: Verifiable Generative Provenance for Multimodal Tool-Using Agents
di: Yu, Bihui, et al.
Pubblicazione: (2026)

The Art of Building Verifiers for Computer Use Agents
di: Rosset, Corby, et al.
Pubblicazione: (2026)

Gym-Anything: Turn any Software into an Agent Environment
di: Aggarwal, Pranjal, et al.
Pubblicazione: (2026)

Beyond Turn Limits: Training Deep Search Agents with Dynamic Context Window
di: Tang, Qiaoyu, et al.
Pubblicazione: (2025)