ComputerSD: Online Self-Distillation from Real-Time Feedback for Computer-Use Agents

arXiv:2609.40253 · cs.CV, cs.AI · Submitted 2026-09-30 · Read on arXiv

cs.CV, cs.AI

Submitted: 2026-09-30

Updated: 2026-10-01

Code: https://github.com/ZJU-REAL/ComputerSD

Terminology

• GRPO — 53× in this paper · explained in 6 episodes
• Analyzer — 42× in this paper · explained in 1 episode
• Distillation — 31× in this paper · explained in 2 episodes
• Self-distillation — 25× in this paper · explained in 6 episodes
• Consistency — 14× in this paper · explained in 3 episodes
• Reinforcement Learning — 7× in this paper · explained in 4 episodes
• Ablation — 6× in this paper · explained in 1 episode
• Benchmark — 5× in this paper · explained in 2 episodes
• Fine-Tuning — 5× in this paper · explained in 5 episodes
• Generalization — 4× in this paper · explained in 13 episodes
• Verifier — 4× in this paper · explained in 2 episodes
• International Conference on Machine Learning — 3× in this paper
• On-Policy Distillation — 3× in this paper · explained in 3 episodes
• On-policy Self-Distillation (OPSD) — 3× in this paper · explained in 2 episodes
• Ablation Studies — 2× in this paper · explained in 1 episode
• GRPO Objective — 2× in this paper · explained in 2 episodes
• Online Reinforcement Learning — 2× in this paper · explained in 2 episodes
• Teacher-Student Gap — 2× in this paper · explained in 2 episodes
• Verification — 2× in this paper · explained in 2 episodes
• Alignment — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Continual Learning — 1× in this paper · explained in 2 episodes
• Core — 1× in this paper · explained in 2 episodes
• Credit assignment — 1× in this paper · explained in 3 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Generalizability — 1× in this paper · explained in 6 episodes
• KL Regularization — 1× in this paper · explained in 2 episodes
• Multimodal Reasoning — 1× in this paper · explained in 5 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Twelfth International Conference on Learning Representations — 1× in this paper
• alpha — 1× in this paper · explained in 1 episode

Sources

• Qwen3-VL Technical Report
• Seed1.5-VL Technical Report
• Kimi K3: Open Frontier Intelligence
• Efficient Multi-turn RL for GUI Agents via Decoupled Training and Adaptive Data Curation
• ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data
• UI-S1: Advancing GUI Automation via Semi-online Reinforcement Learning
• Self-Distilled Agentic Reinforcement Learning
• SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization
• UI-TARS: Pioneering Automated GUI Interaction with Native Agents
• Skill-SD: Skill-Conditioned Self-Distillation for Multi-turn LLM Agents
• OpenCUA: Open Foundations for Computer-Use Agents
• OpenClaw-RL: Train Any Agent Simply by Talking
• SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning
• EvoCUA: Evolving Computer Use Agents via Learning from Scalable Synthetic Experience
• Step-GUI Technical Report
• OPID: On-Policy Skill Distillation for Agentic Reinforcement Learning
• SWIFT:A Scalable lightWeight Infrastructure for Fine-Tuning
• MAI-UI Technical Report: Real-World Centric Foundation GUI Agents

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models