CUA-Master: Scaling Computer-use Agents through Open-World Recursive Improvements
In shortCUA-Master introduces a double-loop recursive framework that uses open-world data to continuously improve computer-use agents.
Published 2 Nov 2026
4 Nov 2026
200 papers that day.
Picks that day
Advances in Agentic Computer Graphics
In shortThe paper proposes a taxonomy and a literature analysis system for agentic computer graphics research.
Published 31 Oct 2026
Everything else
198 more papers from this day- Oct 30 Wave Forcing: Towards Speed-of-Light Streaming Video Generation
- Nov 2 CoworkOS:Scaling Agent Coworkers for Real-world Automation
- Oct 29 Video Generation Meets Agent Harness: Agentic Video Generation, Agentic World Modeling and Recursive Self-Improvement
- Oct 29 From Fragmentation to Fusion: A Survey and Roadmap for Omnimodal Embeddings
- Oct 31 NorthCUA Technical Report: Turbocharging Computer-Use Agents through Experience at Scale
- Nov 2 Reviso: Not All Visual Evidence Deserves Equal Attention in Video Captioning
- Oct 19 Lost in Recovery: Demystifying Recovery Behavior of Computer-Use Agents via Goal-Oriented Action Replay
- Oct 25 SOMA: A Benchmark for Fine-Grained Egocentric Behavior and Body-Motion Understanding
- Nov 2 DR Pixel: Page-Native Deep Research with Vision-Language Models
- Oct 31 SWE-Trail: History-Guided Trajectory Collection for Coding Agent Training
- Oct 31 CrossSWE: Benchmarking Cross-Repository Joint Development for Coding Agents
- Oct 29 DecisionRank: On-Policy Distillation for Decision-Model Rerankers
- Nov 2 IdeaTaste: Do LLMs Share the Research Taste of Human Researchers?
- Nov 2 Library of Layers (LoL): Adaptively Ordering Transformer Layers at Runtime
- Nov 2 PhotoGuider: Composition-Aware Cropping and 360$^{\circ}$ View Framing with Explainable Photographic Assessments
- Oct 31 Can Large Language Model Agents Learn by Watching Tutorial Videos?
- Nov 2 History Forcing: Distilling History-Dependent Continuations for Long-Horizon Video World Models
- Nov 1 LEANGUARD: Lean-Verified Guardrails for Tool-Using Agents
- Oct 28 WorldFlow: Joint Video and 3D Motion Prediction via Large-Scale Pretraining
- Oct 31 Democratizing Robot-Use Agents: A Unified Harness with Open Models
- Oct 27 A Tutorial on Generative Models for Music Audio
- Oct 27 Cross-Primitive Consistency in Jev
- Oct 29 TinyAstral: Transferring Self-Evolving Harnesses to Tiny Generalist Manipulation Agents
- Oct 29 Diagnosing the Reference Gap: What Visual Scaffolds Can and Cannot Fix in Multimodal Reasoning
- Oct 27 On-Policy Self-Distillation with Teacher Evolution
- Oct 29 DeFT-RAG: Decomposing Multi-Hop Questions into Self-Contained Sub-Questions with Reusable Answers
- Oct 28 TSFLab: A Self-Improving Agent-Agnostic Workbench for Time Series Forecasting Research
- Oct 26 GEPA-Curator: Curated Learning for Self Improving Agents
- Nov 2 Avatar Intelligence: Amplifying Human Agency Through Persistent Personal Agents
- Oct 31 Order-Only On-Policy Distillation
- Oct 28 Where Do Vision Language Models Fail at 3D Reasoning?
- Nov 1 When Does Latent Prediction Error Support Physical Surprise Claims in Video World Models?
- Oct 29 BYOD: Build Your Own DLM - Efficient Autoregressive-to-Diffusion Language Model Conversion
- Nov 2 Measuring AI Agents as Teammates with Collaborative Intelligence
- Oct 22 Advancing SVD-based LLM Compression via Layer-Wise Error Model Search
- Oct 28 MAServeBench: Benchmarking Multi-Agent LLM Serving Systems with Hierarchical Collaboration Workloads
- Nov 2 FLAMIA: FLAsh MIcroscaling Attention for Fast and Causally Safe Training on Blackwell
- Oct 10 SIMIT: Self-Improving Vision-Language Models via Imagination at Test-Time
- Oct 30 StreamDuo: A Live Commentator and a Research Agent for Unseen Games
- Oct 26 Multi-Agent Relay Thinking
- Oct 29 DAMI: Dual-Axis Memory Initialization for Enhanced Long-Context Retrieval in Gated Linear Attention
- Nov 2 Can Coding Agents Sustain Continual Evolution without Forgetting?
- Oct 19 ProVe: Proposer-Verifier Decoding
- Nov 2 TaoMate-FVSR:Audio-Guided Facial Video Restoration
- Nov 2 From FAIR to AI-FAIR Metadata-First Infrastructure for AI-Enabled Science
- Nov 2 Lab2Sim: Turning Real-World Experiment Videos into Interactive Virtual Experiments
- Nov 2 CR-Bench-v2: Evaluating the Real-World Utility of AI Code Review Agents
- Oct 14 When Morphs Look Better: Face Image Quality as a Training-Free Signal for Morphing Attack Detection
- Oct 29 Self-Improvement with Auxiliary Rewards: Learning from Verified Traces and Evaluating Transfer
- Nov 2 SpecPilot: Autonomous Algorithm Discovery and Systems Optimization for Speculative Decoding
- Nov 2 Benchmark Prediction with Sparse and Unpaired Cached Responses
- Nov 2 SurgPace: Complexity-Aware Progressive Distillation for Surgical Multimodal Large Language Models
- Nov 2 RouteREPA: Routed Representation Alignment for Just Image Transformers
- Nov 2 MoviEdit: Long-form Multi-Shot Video Editing Made Easy
- Nov 2 Multi-Teacher Reasoning Distillation for LLM Recommendation with Self-Exploration
- Nov 2 WebHarbor: Docking Real Websites for Evolving GUI Agent Environments
- Nov 2 D&A: Decoupling Description and Assessment Enables VLMs as Zero-Shot Robotic Reward Models
- Nov 2 SAGE (Subjectivity-Aware Generation Estimator): A Linguistic Framework for AI-Generated Review Detection *
- Nov 2 EviCast: Forecasting Retrieval Gains Through Shared Response Calibration
- Oct 29 AuditFL: A Contract-Backed Clearing Layer for Open Federated Learning
- Nov 2 DynaSolver: A Neural Operator for Autoregressive 4D Flow Prediction with Dynamic Boundaries
- Nov 2 Contrastive Adapter Training and Consensus Knowledge Distillation for Multi-Source-Free Domain Adaptation in Skin Cancer Diagnosis
- Nov 1 Ask, Don't Equip: Question-Driven Coding Agents for Deep Kernel Optimization
- Nov 2 RASP: Read-All, Sparse-Plasticity Continual Learning in a Stationary-Size LoRA
- Nov 2 TrafficInstruct: A Multi-Task Network Traffic Dataset and Benchmark for Instruction Tuning
- Nov 2 SQLoom: Set-Contrastive Learning of Syntactic, Semantic, and Logical Dependencies for Text-to-SQL
- Nov 2 ENGINE: Endogenous Variational MultiScale Optimization for Zeroth-Order LLM Fine-Tuning
- Nov 2 Axion 1.0: Open Agent Foundation Models, Simplified
- Nov 2 MIRA: Reinforcing Multimodal Reasoning via Deceptive Contextual Augmentation
- Nov 2 BLPO: Beyond-Local Policy Optimization for Long-Horizon LLM Agents
- Nov 2 PGuard: A Native, Streaming, and Plug-in Guardrail for Multimodal Large Language Models
- Nov 2 Accelerating LLM Pretraining with Zeroth-Order Curvature on Idle Serving Compute
- Nov 2 UPSHIFT: User Preference Steering from Human-AI Interaction Feedback Traces
- Nov 2 DexArena: A Unified Benchmark for Long-Horizon Dexterous Manipulation
- Nov 2 DeliverBench: Benchmarking AI Agents on Delivering Realistic Multi-Stage Professional Projects
- Nov 2 ASCoR: Asymmetric Semantic-Spatial Learning for Remote Sensing Domain Generalization
- Nov 2 CISA: Retrofitting Dense Attention Models with Chunk-Indexed Sparse Attention
- Nov 2 Multimodal Prompt Learning with Dual-Granularity Contrastive Alignment for Preoperative Prediction of Lung Adenocarcinoma Invasiveness Using 3D CT
- Nov 2 Efficient Hybrid Distillation: Synergizing Score and Adversarial Objectives for One-Step Diffusion
- Nov 2 Comparative study of global pooling for pre-departure ship fuel consumption prediction: Advantages over per-ship and adaptation-based approaches
- Nov 2 SpecOPD: Branch-Parallel On-Policy Distillation for Speculative Decoding
- Nov 2 OmniOPD: Stable On-Policy Distillation for Joint Audio-Video Generation
- Nov 2 SomaAlign: Reliability-Aware Multimodal Representation Learning for Soft Robotic Grasping
- Nov 2 Hindsight Credit Assignment over Trees for Agentic RL
- Nov 2 HistoTx: Early fusion of H&E images and spatial transcriptomics at varying spatial transcriptomics resolution with self-supervised learning
- Nov 2 Reap: Uncovering Monte Carlo proof search with a lightweight model
- Nov 2 PriCBMs: Multi-granular Concept Bottleneck Vision-Language Models for Visual Privacy Recognition
- Nov 2 Variable names provide priors: semantic grounding enables data-efficient numerical prediction by large language models
- Nov 2 Latent Diffusion-GAN: Adversarial Learning in the Autoencoded Latent Space
- Nov 2 They Know Where It Is, But Not What It Says: A Bilingual Hallucination Benchmark of Hadith Recall in Open LLMs
- Nov 2 FORGE: Fault-Oriented Rework Code Generation for Executable Interlocking Assembly
- Nov 2 Benchmark of THReD: Evaluating an LLM Agent and Its Preprocessing Tools for Turning Electronic Health Records into AI-Ready Datasets
- Nov 2 Think Globally, Generate Personally: Multi-View Thinking with Adaptive Generation for Generative Recommendation
- Nov 2 As Expected? Efficient LLM Planning via Expectation-Observation Consistency Verification
- Nov 2 MirrorComm: A Communication-Efficient Cooperative Perception Framework via Mirrored World Models
- Nov 2 Efficient Closure Learning in Dynamical Systems: A Comparison of Data-Assimilated and Embedded Approaches
- Nov 2 Structured Visual Landscape: Generating Preferred Representations in Biological and Artificial Neural Networks
- Nov 2 BISECT: Bilevel Spectral Decomposition for Low-Rank Continual Learning
- Nov 2 The Cost of Mismatch: Noise Amplification in Zeroth-Order Reinforcement Learning
- Nov 2 ScienceCUA: Resource-to-Skill Construction and Execution-Guided Skill Evolution for Scientific Computer Use Agents
- Nov 2 From Local Skills to Long-Horizon Web Tasks: Progressive Skill Exploration for LLM Web Agents
- Nov 2 Bayesian Sequential Optimal Experimental Design for Single-Pixel Imaging using Reinforcement Learning
- Nov 2 TSB-SEG: A Systematic Time-Series Segmentation Benchmark
- Nov 2 Training-Time Domain Transfer for Generator-Free Diagnostics on Novel Modalities in Computational Pathology
- Nov 2 Efficient Detailed Scheduling of Multiproduct Pipelines using Action-Decoupled Deep Reinforcement Learning
- Nov 1 TRIO: Task Refinement with Individual Optimization for Retrieval-Augmented Generation
- Nov 2 HLSClaw: Bringing Vibe Coding to High-Level Synthesis through Skill-Based Agentic Harness
- Nov 2 Beyond Policy Patches: Distilling RL Specialists into Vision-Language-Action Policies
- Nov 2 Investigating the effects of the patch size in Time Series Foundation Models
- Nov 2 SMILE: A Structured Multi-Agent Clinical Reasoning for Liver Ultrasound Understanding
- Nov 2 RLiD: Reinforcement Learning in the Decision Plane for Language Agents and LLMs
- Nov 2 From Natural Language to Exact Cover: A Neuro-Symbolic Approach to Zebra Puzzles
- Nov 2 Sonar-MoE: In-Backward Expert Updates for Memory-Efficient Mixture-of-Experts Training
- Nov 2 PlantVLM-Edge: Quantized Vision-Language Models for On-Device Crop Health Diagnosis
- Nov 2 CoLa3D: Composable Latent 3D Decomposition
- Nov 2 DistDebug-Bench: Can LLM Agents Diagnose Bugs in Distributed Systems?
- Nov 2 VIAS: Value-Isolating Activation Steering for Multi-Value Alignment and Compliance for Organisations
- Nov 2 Tilted Convexity and an Exact Offline-Online Separation
- Nov 2 VidDub: Replacement-Aware Distillation for Two-Step Video Dubbing
- Nov 1 Every Pixel Is an Option: A System One Model for Medical Ultrasound Biometry
- Nov 2 ArabGeoText: Tool-Augmented Vision-Language Models for Arabic Geospatial Text Spotting
- Nov 1 The SIMPLE Law for Energy Cost of LLM Inference
- Nov 2 R$^2$-Omni: Reducing Structural and Precision Redundancy in Omni-LLMs for Long-Form Generation
- Nov 2 Dhārā Bench: An Evidence-Oriented Retrieval Benchmark for Indian Knowledge Systems
- Nov 2 ViAdminShift: A Vietnamese Benchmark for Event-Level Knowledge Updates Built from the 2025 Administrative Reform
- Nov 2 From PID to Reinforcement Learning in Building HVAC Control: A Control-Architecture Review of Tuning Strategies, Formulations, and Deployment Trade-offs
- Nov 2 A Fine-Grained Hierarchy and Benchmark for State Tracking in Language Models
- Nov 2 Networked AI: Architecture, Theory, and Applications
- Nov 2 PRIME: Predictive Routing of Interventions by Modeling Effects for Scientific Ideation
- Nov 2 Utility-Aware Generative Recommendation: Utility-Enriched Semantic Codes and Utility-Guided Decoding
- Nov 2 Balancing Representations by Identifying and Generating Under-represented Data
- Nov 2 Why Tabular Foundation Models Excel on Relational Data They Have Never Seen
- Nov 2 Bridging Low-Level Image Fusion and High-Level Semantic Understanding
- Nov 2 Solv3R: 3D Looped Transformer as a Multi-view Solver
- Nov 2 Kolmogorov-Arnold Networks vs. Multi-Layer Perceptrons: A Rigorous Statistical Benchmark on Clinical Tabular Data
- Nov 2 Disen-Forcing: Disentangling Semantic Anchoring from Motion for Autoregressive Video Diffusion
- Nov 2 Stop Handcrafting Your Engine! GenDB-V: Towards AI-Generated and Formally Verified Database Systems
- Nov 2 LipLingo: CNN Model for Lip Reading
- Nov 2 EffComp: Efficient Prompt Compression via Hybrid Reinforcement & Supervised Learning
- Nov 2 DINOFAS: Bonafide-Centric Representation Learning for Face Anti-Spoofing
- Nov 2 GeoGuesser Bench: Benchmarking Vision-Language Agents on Interactive Geolocation
- Nov 2 EEFA: A Framework for the Ethical Evaluation of AI Agents
- Nov 2 Energy-Based Policy Orchestration
- Nov 2 FindLink: Learning to Assess Scientific Connections from Source-Grounded Premises
- Nov 2 PixelBench: Can LLMs Understand and Generate Images Pixel by Pixel?
- Nov 2 Tune the Baseline First: Most of Muon's Scaled Weight Decay Gain Is a Tuning Gap, but Its Small Real Advantage Grows With Model Size
- Nov 2 INTERACT: Learning Interaction-Aware World Dynamics from Driving Videos for Autonomous Driving
- Nov 2 Towards Multi-Value Alignment via Value Localization in LLMs
- Nov 2 A Novel Federated Learning Framework for Defending Against Gradient Inversion Attacks
- Nov 2 DiabAgent: Toward Agentic Physiological Control
- Nov 2 FedReady: Bounded Agents for Federation Formation
- Nov 2 NitiBench+: A Temporal Thai Legal Question Answering Benchmark Across 17 Domains
- Nov 2 Progressive Multi-Scale Super-Resolution via Cascaded Bicubic Anchors and Inter-Scale Mutual Refinement
- Nov 2 CrowdForge: Effects of Audio and Visual Audience Participation Modalities on Agency, Collaboration, and Engagement in AI-Mediated MR Performances
- Nov 2 ReVA-HPE: Relative 6DoF Head Pose Estimation with Synthetic Pose Supervision and Personalized Virtual Anchors
- Nov 2 Toward Knowledge-Centric AI: Discovering, Internalizing, and Using Explicit Knowledge Across Agents and Generations
- Nov 2 PaddleMaterials: An End-to-End Deep Learning Toolkit for Materials Science
- Nov 2 Controlling Sharpening in LLM Post-Training
- Nov 1 DepthGraft: Structural Regularization through Hierarchical Cross-Layer KV Reconstruction
- Nov 2 Behavioral Affinity Transduction for Zero-Shot Vision-Language Classification
- Nov 2 ComplianceAtlas: A Taxonomy-Driven Agentic AI Framework for Automated AI Act Gap Analysis and Remediation
- Nov 2 Towards a Trustworthy and Governable Internet of Agentics: An Architectural Perspective on Protocols, Systems, and Services
- Nov 2 Q-CamTuning: A Multimodal Large Language Model for Fine-Grained Quality Reasoning in Livestreaming Camera Tuning
- Nov 2 ILR-SMO: Iterative Latent Refinement for Robust Spatial Multi-Omics Integration
- Nov 2 JABER: Sequential Quality Control for Human-AI Data Annotation under Shared Bias
- Nov 2 Reimagining computational quantum research with AI scientists
- Nov 2 Discovering hierarchical governing equations for community-structured complex network dynamics with LLM agents
- Nov 2 Unlocking the Potential of Vision Foundation Models for Multi-Task Dense Prediction via Mixture of Task Adapters
- Nov 2 GaussFlaw: Fine-Grained Perceptual Diagnosis for 3D Gaussian Splatting
- Nov 2 Trace4D: Grounded Spatiotemporal Reasoning via 4D State Sequences
- Nov 2 What Drives the Zero-to-One Jump? Diagnosing and Steering Hard-Prompt Learning in RLVR
- Nov 2 VioTech: Frame-Level Violin Playing Technique Detection with Multi-Scale Mixture-of-Experts
- Nov 2 VerdictAD: Few-Shot Anomaly Detection via Decision-Guided Refinement
- Nov 2 Adaptive Localization of Knowledge Negation for Continual LLM Unlearning
- Nov 2 W2A: Distilling World Priors into Action Models for Real-Time Robotic Control
- Nov 2 AVID: A 5T fMRI Dataset for Benchmarking Auditory-induced Visual Mental Imagery Decoding
- Nov 2 BasisKV: Value Latents for Communication and Key Routing
- Nov 2 Probing Local Conditional Fit for Diffusion Model Membership Inference
- Nov 2 Cumulative and Audited Guardrail Tool Evolution for LLM Agent Safety
- Nov 2 Fast-Slow Evolutionary Occupancy Prediction via Controlled Dynamics
- Nov 2 Gnomon4D: Learning Where and When to Focus for Geometric Motion-Grounded World-Action Modeling
- Nov 2 Harvesting SWE Benchmarks from Wild Vibe Coding Sessions
- Nov 2 Blueprint2CAD: Benchmarking Foundation Models on Engineering Drawing-to-CAD Render Correspondence
- Nov 2 EgoActionBench: Benchmarking Dense Action Captioning for Egocentric Human Videos
- Nov 2 Isekai3D SDG: A Platform for Diverse Synthetic Gameplay Visual Data
- Nov 2 TAMPAgent: Agentic Belief-Space Planning for Mobile Manipulation
- Nov 2 Can LLM Agents Be Forward-Deployed Engineers? Requirement Discovery and Delivery for Enterprise Text-to-SQL
- Nov 2 Can LLM Agents Improve Imperfect Earth System Model Parameterizations?
- Nov 2 PanoTac: A Dense Three-Axis Tactile Sensor for Robust Touch-Centric Manipulation
- Nov 2 A Bayesian Framework for Safe Optimal Control of Unknown Systems from Input-Output Data
- Nov 2 Low-Rank Clebsch--Gordan Coupling for Equivariant Spherical Forecasting
- Nov 1 TaoMate-HD: Progressive-Resolution Autoregressive Audio-Video Generation
- Nov 2 Can We Stop the Backtest Yet? Anytime-Valid Promotion Tests for Adaptive Financial Research Agents
- Nov 2 Certifying Graph Neural Networks Against Label and Structure Poisoning
- Nov 2 An Axiomatic Framework for Reinforcement Learning in Open Multi-Agent Systems
- Nov 2 ForceLDM: A Force-aware Latent Dynamics Model for Contact-Rich Manipulation
- Nov 2 Anomaly-ranked confirmation slows new-class learning
- Nov 2 HyperFlow: Class-Incremental Semantic Change Detection via Hyperbolic Flow