ToolCUA: Towards Optimal GUI-Tool Path Orchestration for Computer Use Agents

arXiv:2605.12481 · cs.AI · Submitted 2026-05-12 · Read on arXiv

cs.AI

Submitted: 2026-05-12

Updated: 2026-09-19

Code: https://github.com/X-PLUG/ToolCUA

Project page: https://x-plug.github.io/ToolCUA

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Accuracy — 31× in this paper · explained in 1 episode
• Action Space — 30× in this paper · explained in 1 episode
• Benchmark — 13× in this paper · explained in 2 episodes
• Grounding — 13× in this paper · explained in 3 episodes
• Reinforcement Learning — 10× in this paper · explained in 4 episodes
• Ablation — 8× in this paper · explained in 1 episode
• Fidelity — 6× in this paper · explained in 2 episodes
• GRPO — 6× in this paper · explained in 6 episodes
• Fine-Tuning — 4× in this paper · explained in 5 episodes
• Foundation Model — 4× in this paper · explained in 3 episodes
• Generalization — 4× in this paper · explained in 13 episodes
• Verification — 4× in this paper · explained in 2 episodes
• Abstraction — 3× in this paper · explained in 1 episode
• Average Completion Steps — 3× in this paper
• Benchmarking — 3× in this paper · explained in 3 episodes
• Foundation Models — 3× in this paper · explained in 7 episodes
• Aggregation — 2× in this paper · explained in 1 episode
• Consistency — 2× in this paper · explained in 3 episodes
• Core — 2× in this paper · explained in 2 episodes
• Multi-agent Collaboration — 2× in this paper · explained in 2 episodes
• Tool Invocation Rate — 2× in this paper
• Visual Grounding — 2× in this paper · explained in 2 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Ablation study — 1× in this paper · explained in 1 episode
• Failure Modes — 1× in this paper · explained in 3 episodes
• Generalizability — 1× in this paper · explained in 6 episodes
• Group Relative Policy Optimization — 1× in this paper
• Group Relative Policy Optimization (GRPO) — 1× in this paper · explained in 5 episodes
• Markov Decision Process (MDP) — 1× in this paper · explained in 10 episodes
• Multi-Agent System — 1× in this paper · explained in 5 episodes
• Multimodal Reasoning — 1× in this paper · explained in 5 episodes
• Reinforcement Learning (RL) — 1× in this paper · explained in 24 episodes
• Reward Function — 1× in this paper · explained in 2 episodes
• Supervised Fine-Tuning — 1× in this paper
• Supervised Fine-Tuning (SFT) — 1× in this paper · explained in 8 episodes
• Test-time Scaling — 1× in this paper · explained in 2 episodes
• Transferability — 1× in this paper · explained in 4 episodes

Sources

• Agent S2: A Compositional Generalist-Specialist Framework for Computer Use Agents
• Qwen2.5-VL Technical Report
• Windows Agent Arena: Evaluating Multi-Modal OS Agents at Scale
• Tool-Star: Empowering LLM-Brained Multi-Tool Reasoner via Reinforcement Learning
• ReTool: Reinforcement Learning for Strategic Tool Use in LLMs
• Scaling Agents for Computer Use
• DeepEyesV2: Toward Agentic Multimodal Model
• OSWorld-MCP: Benchmarking MCP Tool Invocation In Computer-Use Agents
• CUA-Suite: Massive Human-annotated Video Demonstrations for Computer-Use Agents
• Efficient Multi-turn RL for GUI Agents via Decoupled Training and Adaptive Data Curation
• MM-BrowseComp: A Comprehensive Benchmark for Multimodal Browsing Agents
• PC-Agent: A Hierarchical Multi-Agent Collaboration Framework for Complex Task Automation on PC
• AutoGLM: Autonomous Foundation Agents for GUIs
• ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data
• Visual-RFT: Visual Reinforcement Fine-Tuning
• ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay
• UI-R1: Enhancing Efficient Action Prediction of GUI Agents by Reinforcement Learning
• GUI-R1 : A Generalist R1-Style Vision-Language Action Model For GUI Agents
• ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs
• UI-TARS: Pioneering Automated GUI Interaction with Native Agents

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