DeepRead
Search
Search
Dark mode
Light mode
Explorer
Popular Tags
#VLM
#agentic-RL
#gui-agent
#web-agent
#LLM
#VLA
#computer-use
#task-planning
#manipulation
#imitation-learning
Tag: computer-use
150 items with this tag.
Aug 20, 2026
Agent Harness 的组件归因：外置 state、fresh-context 执行与独立验证，哪一个在起作用
survey
task-planning
LLM
computer-use
Aug 20, 2026
Computer-Use Agents: A Unified Survey of Models, Learning, Environments, Evaluation, and Deployment
survey
gui-agent
computer-use
web-agent
mobile-agent
os-agent
agentic-RL
Aug 20, 2026
Self-Initiated Fork：分支决策作为 GUI agent 的可学习动作
gui-agent
computer-use
agentic-RL
Aug 20, 2026
MismatchTriage: Measuring and Closing Recovery-Selection Regret in GUI Agents
gui-agent
computer-use
recovery
counterfactual
Aug 20, 2026
AFE-MiniSuite: Agent-Facing Web Runtime Affordance 的因果消融
gui-agent
web-agent
computer-use
environment
agent-facing-runtime
Aug 20, 2026
UI-Mate: Advancing Open-Weight Foundation GUI Agents with In-Context Demonstrations
computer-use
gui-agent
agentic-RL
Aug 20, 2026
Screenshots or Tools? Eliciting Tool Use and Managing Multimodal Context in Hybrid GUI-MCP Computer-Use Agents
computer-use
gui-agent
agentic-RL
Aug 20, 2026
Qwen-CUA: Native Computer Use for (almost) Everything
computer-use
gui-agent
agentic-RL
Aug 20, 2026
Ouroboros: A Self-Developing Frontier Coding Agent with Reviewed Core Evolution
agentic-RL
LLM
computer-use
Aug 20, 2026
LongHorizon-Harness: Advancing Long-Horizon Agents for Real-World Tasks
computer-use
task-planning
gui-agent
Aug 20, 2026
Invisible Ink Threats: Adversarial Goals Behind Legitimate Tasks in Computer-Use Agents
computer-use
gui-agent
hci
Aug 20, 2026
GUI-Lens: Coarse-to-Fine Cropping for GUI Grounding with General-Purpose VLMs
gui-agent
VLM
computer-use
Aug 20, 2026
Qwen-UI-Agent Technical Report: Toward Next-Generation Real-World Centric Foundation GUI Agents
gui-agent
computer-use
agentic-RL
Aug 20, 2026
A11y-Compressor: A Framework for Enhancing the Efficiency of GUI Agent Observations through Visual Context Reconstruction and Redundancy Reduction
gui-agent
computer-use
Aug 20, 2026
WindowsWorld: A Process-Centric Benchmark of Autonomous GUI Agents in Professional Cross-Application Environments
gui-agent
computer-use
task-planning
Aug 20, 2026
OSReward: Instituting Standardized Evaluation for Cross-Platform Computer-Use Reward Models
computer-use
gui-agent
agentic-RL
Aug 20, 2026
UI-MOPD: Multi-Platform On-Policy Distillation for Continual GUI Agent Learning
gui-agent
agentic-RL
computer-use
Aug 20, 2026
VLAA-GUI: Knowing When to Stop, Recover, and Search, A Modular Framework for GUI Automation
gui-agent
computer-use
00FF00
Aug 20, 2026
Teach it to stop, not just to click
computer-use
agentic-RL
gui-agent
Aug 20, 2026
How Benchmarks Mis-Score Computer-Use Agents
computer-use
gui-agent
web-agent
benchmark
evaluation
LLM
Aug 20, 2026
TACTILE: Giving Computer-Using Agents Hands and Feet
computer-use
gui-agent
Aug 20, 2026
Step-level Optimization for Efficient Computer-use Agents
computer-use
gui-agent
agentic-RL
Aug 20, 2026
StateAct: Program State, before Pixels, for Long-Horizon Computer-Use Agents
computer-use
gui-agent
task-planning
Aug 20, 2026
Sidekick: Designing Communication for Effective Multitasking with Computer Use Agents
computer-use
gui-agent
Aug 20, 2026
SeekJudge: A Practical Reward Framework for Reinforcement Learning in Computer-Use Agents
computer-use
agentic-RL
Aug 20, 2026
SkillClaw: Let Skills Evolve Collectively with Agentic Evolver
computer-use
task-planning
LLM
Aug 20, 2026
MAGA: Multi-Platform Self-Fusion of GUI Agents via Structured Action Distillation
gui-agent
agentic-RL
computer-use
Aug 20, 2026
See, Think, Act: Teaching Multimodal Agents to Effectively Interact with GUI by Identifying Toggles
gui-agent
computer-use
VLM
Aug 20, 2026
GUI Agents with Reinforcement Learning: Toward Digital Inhabitants
gui-agent
agentic-RL
computer-use
Aug 20, 2026
Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading
computer-use
task-planning
Aug 20, 2026
SCALECUA: Scaling Computer Use Agents with Verifiable Task Synthesis and Efficient Online RL
computer-use
agentic-RL
gui-agent
Aug 20, 2026
KnowAct-GUIClaw: Know Deeply, Act Perfectly, Personal GUI Assistant with Self-Evolving Memory and Skill
gui-agent
computer-use
task-planning
Aug 20, 2026
Interactive Reward Agent: GUI Task Evaluation via Environment-State Verification
gui-agent
computer-use
agentic-RL
Aug 20, 2026
OpenMobile: Building Open Mobile Agents with Task and Trajectory Synthesis
gui-agent
computer-use
Aug 20, 2026
Odysseys: Benchmarking Web Agents on Realistic Long Horizon Tasks
web-agent
computer-use
gui-agent
Aug 20, 2026
RESOURCE2SKILL: Distilling Executable Agent Skills from Human-Created Multimodal Resources
computer-use
task-planning
VLM
Aug 20, 2026
Do GUI Agents Believe Their Eyes? Diagnosing State-Belief Reliance on Pixels versus Structure
gui-agent
computer-use
VLM
Aug 20, 2026
EvoCUA-1.5: Online Reinforcement Learning for Multi-turn Computer-Use Agents
computer-use
agentic-RL
gui-agent
Aug 20, 2026
CUA-Gym: Scaling Verifiable Training Environments and Tasks for Computer-Use Agents
agentic-RL
computer-use
gui-agent
Aug 20, 2026
Qwen-AgentWorld: Language World Models for General Agents
world-model
agentic-RL
computer-use
Aug 20, 2026
BraveGuard: From Open-World Threats to Safer Computer-Use Agents
computer-use
gui-agent
Aug 20, 2026
PrivacyAlign: Contextual Privacy Alignment for LLM Agents
computer-use
agentic-RL
LLM
Aug 20, 2026
BAMI: Training-Free Bias Mitigation in GUI Grounding
gui-agent
computer-use
VLM
Aug 20, 2026
Agents' Last Exam
computer-use
gui-agent
LLM
Aug 20, 2026
When Lower Privileges Suffice: Investigating Over-Privileged Tool Selection in LLM Agents
computer-use
LLM
agentic-RL
Aug 20, 2026
Agentic Abstention: Do Agents Know When to Stop Instead of Act?
computer-use
web-agent
agentic-RL
Aug 20, 2026
OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks
computer-use
gui-agent
task-planning
Aug 20, 2026
Capable but Careless: Do Computer-Use Agents Follow Contextual Integrity?
computer-use
gui-agent
Aug 20, 2026
Crab: A Semantics-Aware Checkpoint/Restore Runtime for Agent Sandboxes
computer-use
agentic-RL
Aug 20, 2026
OS-Oracle: A Comprehensive Framework for Cross-Platform GUI Critic Models
gui-agent
computer-use
VLM
Aug 20, 2026
Why Are GUI Agents Correct but Late? Decode on the Decision-Time Critical Path, Tested with Pre-Compiled Policy Trees
gui-agent
computer-use
task-planning
Aug 20, 2026
Naive Visual Memory is Not Enough: A Failure-Mode Study of GUI Agents
gui-agent
computer-use
Aug 20, 2026
iSHIFT: Lightweight Slow-Fast GUI Agent with Adaptive Perception
gui-agent
computer-use
VLM
Aug 20, 2026
ClawGUI: A Unified Framework for Training, Evaluating, and Deploying GUI Agents
gui-agent
agentic-RL
computer-use
Aug 20, 2026
MyPCBench: A Benchmark for Personally Intelligent Computer-Use Agents
computer-use
gui-agent
web-agent
Aug 20, 2026
AdapAction: Adaptive Target Action Backdoor Attack against GUI Agents
gui-agent
computer-use
VLM
Aug 20, 2026
Claw-Eval-Live: A Live Agent Benchmark for Evolving Real-World Workflows
computer-use
agentic-RL
LLM
Aug 20, 2026
WeaveBench: A Long-Horizon, Real-World Benchmark for Computer-Use Agents with Hybrid Interfaces
computer-use
gui-agent
agentic-RL
Aug 20, 2026
MobileForge: Annotation-Free Adaptation for Mobile GUI Agents with Hierarchical Feedback-Guided Policy Optimization
gui-agent
agentic-RL
computer-use
Aug 20, 2026
Claw-Eval: Toward Trustworthy Evaluation of Autonomous Agents
computer-use
agentic-RL
LLM
Aug 20, 2026
Dive into Claude Code: The Design Space of Today's and Future AI Agent Systems
computer-use
web-agent
Aug 20, 2026
MVP: Multiple View Prediction Improves GUI Grounding
gui-agent
VLM
computer-use
Aug 20, 2026
Multi-Agent Computer Use
computer-use
gui-agent
task-planning
Aug 20, 2026
Workspace-Bench 1.0: Benchmarking AI Agents on Workspace Tasks with Large-Scale File Dependencies
computer-use
gui-agent
LLM
task-planning
Aug 20, 2026
Learning from Failure: Inference-Time Self-Improvement for Computer-Use Agents
computer-use
gui-agent
agentic-RL
Aug 20, 2026
LUMOS: A Semantic Operating-System Layer for Accessibility-Grounded AI Agents
computer-use
gui-agent
web-agent
Aug 20, 2026
SecAgent: Efficient Mobile GUI Agent with Semantic Context
gui-agent
computer-use
VLM
Aug 20, 2026
SaaS-Bench: Can Computer-Use Agents Leverage Real-World SaaS to Solve Professional Workflows?
computer-use
web-agent
gui-agent
Aug 20, 2026
A History-Aware Visually Grounded Critic for Computer Use Agents
gui-agent
computer-use
VLM
Aug 20, 2026
PIRA-Bench: A Transition from Reactive GUI Agents to GUI-based Proactive Intent Recommendation Agents
gui-agent
computer-use
instruction-following
Aug 20, 2026
STaR-KV: Spatio-Temporal Adaptive Re-weighting for KV Cache Compression in GUI Vision-Language Models
gui-agent
VLM
computer-use
Aug 20, 2026
HATS: Hardness-Aware Trajectory Synthesis for GUI Agents
gui-agent
computer-use
VLM
Aug 20, 2026
OpenComputer: Verifiable Software Worlds for Computer-Use Agents
computer-use
gui-agent
Aug 20, 2026
ShowUI-π: Flow-based Generative Models as GUI Dexterous Hands
gui-agent
computer-use
flow-matching
Aug 20, 2026
GUI vs. CLI: Execution Bottlenecks in Screen-Only and Skill-Mediated Computer-Use Agents
computer-use
gui-agent
task-planning
Aug 20, 2026
GUIDE: A Benchmark for Understanding and Assisting Users in Open-Ended GUI Tasks
gui-agent
computer-use
VLM
Aug 20, 2026
AgentSynth: Scalable Task Generation for Generalist Computer-Use Agents
computer-use
web-agent
task-planning
Aug 20, 2026
ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data
computer-use
gui-agent
VLM
Aug 20, 2026
Evaluating and Easing Hallucinations for GUI Grounding
gui-agent
VLM
computer-use
Aug 20, 2026
LiteGUI: Distilling Compact GUI Agents with Reinforcement Learning
gui-agent
agentic-RL
computer-use
Aug 20, 2026
When Agents Overtrust Environmental Evidence: An Extensible Agentic Framework for Benchmarking Evidence-Grounding Defects in LLM Agents
computer-use
LLM
Aug 20, 2026
Your Agent May Misevolve: Emergent Risks in Self-evolving LLM Agents
agentic-RL
LLM
computer-use
Aug 20, 2026
Agentic Reward Modeling: Verifying GUI Agent via Online Proactive Interaction
agentic-RL
gui-agent
computer-use
Aug 20, 2026
ENVS: Environment-Native Verified Search for Long-Horizon GUI Agents
gui-agent
computer-use
agentic-RL
Aug 20, 2026
CutVerse: A Compositional GUI Agents Benchmark for Media Post-Production Editing
gui-agent
computer-use
Aug 20, 2026
ToolTok: Tool Tokenization for Efficient and Generalizable GUI Agents
gui-agent
computer-use
VLM
Aug 20, 2026
Efficient Multi-turn RL for GUI Agents via Decoupled Training and Adaptive Data Curation
agentic-RL
computer-use
gui-agent
Aug 20, 2026
Code as Agent Harness: Toward Executable, Verifiable, and Stateful Agent Systems
LLM
gui-agent
computer-use
task-planning
Aug 20, 2026
Covering Human Action Space for Computer Use: Data Synthesis and Benchmark
gui-agent
computer-use
Aug 20, 2026
Beyond Binary: Reframing GUI Critique as Continuous Semantic Alignment
gui-agent
computer-use
VLM
Aug 20, 2026
OpenCUA: Open Foundations for Computer-Use Agents
computer-use
gui-agent
VLM
imitation-learning
Aug 20, 2026
Agent Alpha: Tree Search Unifying Generation, Exploration and Evaluation for Computer-Use Agents
computer-use
gui-agent
Aug 20, 2026
ANCHOR: Branch-Point Data Generation for GUI Agents
gui-agent
computer-use
Aug 20, 2026
OS Agents: A Survey on MLLM-based Agents for General Computing Devices Use
computer-use
gui-agent
web-agent
Aug 20, 2026
AutoFocus: Uncertainty-Aware Active Visual Search for GUI Grounding
gui-agent
VLM
computer-use
Aug 20, 2026
Autonomous Continual Learning for Environment Adaptation of Computer-Use Agents
computer-use
agentic-RL
gui-agent
Aug 20, 2026
ZonUI-3B: Competitive GUI Grounding with a 3B VLM Trained on a Single Consumer GPU
gui-agent
VLM
computer-use
Aug 20, 2026
AgentTrust: Runtime Safety Evaluation and Interception for AI Agent Tool Use
computer-use
agentic-RL
Aug 20, 2026
ComputerRL: Scaling End-to-End Online Reinforcement Learning for Computer Use Agents
computer-use
agentic-RL
gui-agent
Params
Aug 20, 2026
CoAct-1: Computer-using Multi-agent System with Coding Actions
computer-use
gui-agent
task-planning
Aug 20, 2026
OmegaUse: Building a General-Purpose GUI Agent for Autonomous Task Execution
gui-agent
computer-use
agentic-RL
Aug 20, 2026
OS-Marathon: Benchmarking Computer-Use Agents on Long-Horizon Repetitive Tasks
computer-use
gui-agent
task-planning
Aug 20, 2026
GUIGuard-Bench: Toward a General Evaluation for Privacy-Preserving GUI Agents
gui-agent
computer-use
VLM
Aug 20, 2026
EvoCUA: Evolving Computer Use Agents via Learning from Scalable Synthetic Experience
computer-use
agentic-RL
gui-agent
Aug 20, 2026
AFRAgent : An Adaptive Feature Renormalization Based High Resolution Aware GUI agent
gui-agent
VLM
computer-use
Aug 20, 2026
WebHarbor: Docking Real Websites for Evolving GUI Agent Environments
web-agent
gui-agent
computer-use
Aug 20, 2026
Scalable Video-to-Dataset Generation for Cross-Platform Mobile Agents
gui-agent
computer-use
video-understanding
Aug 20, 2026
OSWorld-Human: Benchmarking the Efficiency of Computer-Use Agents
computer-use
gui-agent
Aug 20, 2026
MP-GUI: Modality Perception with MLLMs for GUI Understanding
gui-agent
VLM
computer-use
Aug 20, 2026
MCPWorld: A Unified Benchmarking Testbed for API, GUI, and Hybrid Computer Use Agents
computer-use
gui-agent
Aug 20, 2026
CogAgent: A Visual Language Model for GUI Agents
gui-agent
VLM
computer-use
Aug 20, 2026
OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis
gui-agent
computer-use
VLM
Aug 20, 2026
Scaling Computer-Use Grounding via User Interface Decomposition and Synthesis
gui-agent
computer-use
Aug 20, 2026
WebArena: A Realistic Web Environment for Building Autonomous Agents
web-agent
LLM
computer-use
Aug 20, 2026
The BrowserGym Ecosystem for Web Agent Research
web-agent
gui-agent
computer-use
Aug 20, 2026
Agent-X: Evaluating Deep Multimodal Reasoning in Vision-Centric Agentic Tasks
VLM
computer-use
Aug 20, 2026
ScreenSpot-Pro: GUI Grounding for Professional High-Resolution Computer Use
gui-agent
computer-use
Aug 20, 2026
Large Language Model-Brained GUI Agents: A Survey
gui-agent
computer-use
agentic-RL
Aug 20, 2026
OS-ATLAS: A Foundation Action Model for Generalist GUI Agents
gui-agent
computer-use
VLM
Elements
Aug 20, 2026
Agent S2: A Compositional Generalist-Specialist Framework for Computer Use Agents
computer-use
gui-agent
task-planning
Aug 20, 2026
GUI-AIMA: Aligning Intrinsic Multimodal Attention with a Context Anchor for GUI Grounding
gui-agent
VLM
computer-use
Aug 20, 2026
Grounding Computer Use Agents on Human Demonstrations
gui-agent
computer-use
agentic-RL
AvgE
Aug 20, 2026
WindowsAgentArena: Evaluating Multi-Modal OS Agents at Scale
computer-use
gui-agent
Aug 20, 2026
OmniParser for Pure Vision Based GUI Agent
gui-agent
computer-use
VLM
1/3
Aug 20, 2026
Visual Test-time Scaling for GUI Agent Grounding
gui-agent
computer-use
VLM
Aug 20, 2026
UINavBench: A Framework for Comprehensive Evaluation of Interactive Digital Agents
gui-agent
computer-use
VLM
Aug 20, 2026
Sikuli: Using GUI Screenshots for Search and Automation
gui-agent
computer-use
Aug 20, 2026
The Unreasonable Effectiveness of Scaling Agents for Computer Use
computer-use
gui-agent
LLM
Aug 20, 2026
R-WoM: Retrieval-augmented World Model For Computer-use Agents
computer-use
world-model
web-agent
Aug 20, 2026
拔电源测试：GUI Agent 的状态笔记能当 checkpoint 用吗
gui-agent
computer-use
research-idea
Aug 20, 2026
Self-Initiated Fork：让 GUI agent 学会何时分支
gui-agent
computer-use
agentic-RL
Aug 20, 2026
OSWorld-MCP: Benchmarking MCP Tool Invocation In Computer-Use Agents
computer-use
gui-agent
Aug 20, 2026
Restoration Fidelity：回溯没恢复的那部分状态，及其对分支收益与训练数据的污染
gui-agent
web-agent
computer-use
Aug 20, 2026
Personalized Safety for Computer-Use Agents
computer-use
gui-agent
Aug 20, 2026
MGA: Memory-Driven GUI Agent for Observation-Centric Interaction
gui-agent
computer-use
Aug 20, 2026
Iris: Breaking GUI Complexity with Adaptive Focus and Self-Refining
gui-agent
VLM
computer-use
Aug 20, 2026
Recovery-Selection Gap：GUI Agent 的固定恢复策略留下多少可收回的成功率
gui-agent
computer-use
research-idea
Aug 20, 2026
On the Effects of Data Scale on UI Control Agents
gui-agent
computer-use
Aug 20, 2026
Hybrid Verifier-Grounded GUI Runtime
gui-agent
computer-use
environment
verifier
research-idea
Aug 20, 2026
UI-TARS: Pioneering Automated GUI Interaction with Native Agents
computer-use
gui-agent
VLM
Aug 20, 2026
Agent-Facing Web Runtime Affordances
gui-agent
web-agent
computer-use
environment
research-idea
Aug 20, 2026
AFE-MiniSuite: Causal Ablation of Agent-Facing Web Runtime Affordances
gui-agent
web-agent
computer-use
environment
agent-facing-runtime
Aug 20, 2026
CUARewardBench: A Benchmark for Evaluating Reward Models on Computer-using Agent
computer-use
agentic-RL
gui-agent
Aug 20, 2026
Toward Systems Foundations for Agentic Exploration
computer-use
LLM
Aug 20, 2026
A Comprehensive Survey of Agents for Computer Use: Foundations, Challenges, and Future Directions
computer-use
gui-agent
web-agent
Aug 20, 2026
UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning
gui-agent
computer-use
agentic-RL
1-2
Jul 03, 2026
2026-07-03-Autoresearch-AllTopics-Update
computer-use
gui-agent
agentic-RL
VLA
world-model
Jul 01, 2026
2026-07-01-Autoresearch-AllTopics-Update
computer-use
gui-agent
web-agent
agentic-RL
Jun 24, 2026
GUI Environment 近期工作调研与 Agent-Facing Runtime 选题更新
report
gui-agent
computer-use
environment
benchmark
verifier
research-strategy
Jun 23, 2026
Agent-Friendly Environment 简短 Proposal
proposal
gui-agent
environment
computer-use
research-idea