Image de couverture de livre

PRO-CUA: Process-Reward Optimization for Computer Use Agents

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	He, Yifei, Yang, Rui, Bai, Hao, Zhang, Tong, Zhao, Han
Format:	Preprint
Publié:	2026
Sujets:	Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

CUA-Gym: Scaling Verifiable Training Environments and Tasks for Computer-Use Agents
par: Wang, Bowen, et autres
Publié: (2026)

OpenCUA: Open Foundations for Computer-Use Agents
par: Wang, Xinyuan, et autres
Publié: (2025)

ToolCUA: Towards Optimal GUI-Tool Path Orchestration for Computer Use Agents
par: Hu, Xuhao, et autres
Publié: (2026)

CUA-Skill: Develop Skills for Computer Using Agent
par: Chen, Tianyi, et autres
Publié: (2026)

LiteCUA: Computer as MCP Server for Computer-Use Agent on AIOS
par: Mei, Kai, et autres
Publié: (2025)

CUA-Suite: Massive Human-annotated Video Demonstrations for Computer-Use Agents
par: Jian, Xiangru, et autres
Publié: (2026)

EvoCUA: Evolving Computer Use Agents via Learning from Scalable Synthetic Experience
par: Xue, Taofeng, et autres
Publié: (2026)

IntentCUA: Learning Intent-level Representations for Skill Abstraction and Multi-Agent Planning in Computer-Use Agents
par: Lee, Seoyoung, et autres
Publié: (2026)

WebSTAR: Scalable Data Synthesis for Computer Use Agents with Step-Level Filtering
par: He, Yifei, et autres
Publié: (2025)

WebArbiter: A Principle-Guided Reasoning Process Reward Model for Web Agents
par: Zhang, Yao, et autres
Publié: (2026)

On the Reliability of Computer Use Agents
par: Gonzalez-Pumariega, Gonzalo, et autres
Publié: (2026)

ComputerRL: Scaling End-to-End Online Reinforcement Learning for Computer Use Agents
par: Lai, Hanyu, et autres
Publié: (2025)

The Agent Use of Agent Beings: Agent Cybernetics Is the Missing Science of Foundation Agents
par: Wang, Xinrun, et autres
Publié: (2026)

GUI-PRA: Process Reward Agent for GUI Tasks
par: Xiong, Tao, et autres
Publié: (2025)

CaMeLs Can Use Computers Too: System-level Security for Computer Use Agents
par: Foerster, Hanna, et autres
Publié: (2026)

PRO-V-R1: Reasoning Enhanced Programming Agent for RTL Verification
par: Zhao, Yujie, et autres
Publié: (2025)

Process Reward Agents for Steering Knowledge-Intensive Reasoning
par: Sohn, Jiwoong, et autres
Publié: (2026)

Evaluate-as-Action: Self-Evaluated Process Rewards for Retrieval-Augmented Agents
par: Shu, Jiangming, et autres
Publié: (2026)

Mutual Information as Intrinsic Reward of Reinforcement Learning Agents for On-demand Ride Pooling
par: Zhang, Xianjie, et autres
Publié: (2023)

AgentHijack: Benchmarking Computer Use Agent Robustness to Common Environment Corruptions
par: Sun, Jingwei, et autres
Publié: (2026)

RRO: LLM Agent Optimization Through Rising Reward Trajectories
par: Wang, Zilong, et autres
Publié: (2025)

Beyond Correctness: Harmonizing Process and Outcome Rewards through RL Training
par: Ye, Chenlu, et autres
Publié: (2025)

Reward Difference Optimization For Sample Reweighting In Offline RLHF
par: Wang, Shiqi, et autres
Publié: (2024)

Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs
par: Yang, Rui, et autres
Publié: (2024)

Trust Region Reward Optimization and Proximal Inverse Reward Optimization Algorithm
par: Chen, Yang, et autres
Publié: (2025)

Efficient Agent Training for Computer Use
par: He, Yanheng, et autres
Publié: (2025)

Self-Guided Process Reward Optimization with Redefined Step-wise Advantage for Process Reinforcement Learning
par: Fei, Wu, et autres
Publié: (2025)

Training Computer Use Agents to Assess the Usability of Graphical User Interfaces
par: Gao, Alice, et autres
Publié: (2026)

Thinking vs. Doing: Agents that Reason by Scaling Test-Time Interaction
par: Shen, Junhong, et autres
Publié: (2025)

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents
par: Yang, Jingyi, et autres
Publié: (2025)

OpenComputer: Verifiable Software Worlds for Computer-Use Agents
par: Wei, Jinbiao, et autres
Publié: (2026)

MagicGUI-RMS: A Multi-Agent Reward Model System for Self-Evolving GUI Agents via Automated Feedback Reflux
par: Li, Zecheng, et autres
Publié: (2026)

SmartSearch: Process Reward-Guided Query Refinement for Search Agents
par: Wen, Tongyu, et autres
Publié: (2026)

PRO: Enabling Precise and Robust Text Watermark for Open-Source LLMs
par: Xue, Jiaqi, et autres
Publié: (2025)

WebPII: Benchmarking Visual PII Detection for Computer-Use Agents
par: Zhao, Nathan
Publié: (2026)

A Survey on the Optimization of Large Language Model-based Agents
par: Du, Shangheng, et autres
Publié: (2025)

MASPRM: Multi-Agent System Process Reward Model
par: Yazdani, Milad, et autres
Publié: (2025)

Arithmetic Control of LLMs for Diverse User Preferences: Directional Preference Alignment with Multi-Objective Rewards
par: Wang, Haoxiang, et autres
Publié: (2024)

C-World: A Computer Use Agent Environment Creator
par: Xi, Ziqiao, et autres
Publié: (2026)

Step-level Optimization for Efficient Computer-use Agents
par: Wei, Jinbiao, et autres
Publié: (2026)