OS-Copilot: Towards Generalist Computer Agents with Self-Improvement
Zhiyong Wu , Chengcheng Han , Zichen Ding , Zhenmin Weng , Zhoumianze Liu , Shunyu Yao , Tao Yu , Lingpeng Kong
- 🏛 Institutions
- Shanghai AI Laboratory , East China Normal University , Princeton , HKU
- 📅 Date
- February 12, 2024
- 📑 Publisher
- LLMAgents @ ICLR 2024
- 💻 Env
- Desktop Web
- 🔑 Keywords
TLDR
OS-Copilot is a framework for building generalist computer agents that interact with operating-system elements including the web, code terminals, files, multimedia, and third-party applications. The paper instantiates it with FRIDAY, a self-improving embodied agent that learns new application skills over time and reports a 35% improvement over prior methods on GAIA.
Related papers (24)
- Surfer 2: The Next Generation of Cross-Platform Computer Use AgentsOctober 22, 2025 · arXiv
- WorldGUI: An Interactive Benchmark for Desktop GUI Automation from Any Starting PointFebruary 12, 2025 · arXiv
- VeriCUA: Learning Proactive Verification for Reliable GUI Agent RewardsOctober 19, 2026 · arXiv
- Step-Aligned Script Generation with Verification and Recovery for Web Automation TestingOctober 19, 2026 · arXiv
- Adaptation of Computer Use Agents to New Software with User ManualsOctober 16, 2026 · arXiv
- What It Is, Not What It Says: Securing Agentic Browsing Interactions with Web SemanticsOctober 15, 2026 · arXiv
- OpenGCUA: Toward a Fully Open Stack for Generalist Computer UseOctober 15, 2026 · arXiv
- OS-Helix: Unifying GUI Interaction and Code Execution in Native Computer-Using AgentsOctober 15, 2026 · arXiv
- LEASH: Uncertainty-Aware Weak-to-Strong Escalation and Oversight for Computer-Use AgentsOctober 15, 2026 · arXiv
- Why Generate a Click? Plug-in Decision Heads for Web AgentsOctober 14, 2026 · arXiv
- Teaching Agents in their Own Style: Blackbox Teacher Distillation for Web AgentsOctober 14, 2026 · arXiv
- Task-State Governance: A Virtual Machine for Verifiable and Recoverable GUI Agent ExecutionOctober 14, 2026 · arXiv
- A Decade in a Day: Synthesizing Agent-Native Interfaces from Human-Oriented Software EvolutionOctober 11, 2026 · arXiv
- Reflect, Revise, Reuse: Training-Free Skill Evolution for GUI AgentsSeptember 15, 2026 · arXiv
- EchoPath: Execution-Level Replayable Memory for GUI AgentsSeptember 15, 2026 · arXiv
- RSIAgent: Autonomous Exploration for Recursive Self-improvement in New EnvironmentsSeptember 14, 2026 · arXiv
- AutoTailor: Automatic, User-Aligned Capability Selection and Adaptation for Web AgentsSeptember 11, 2026 · arXiv
- CUA-Universe: A Scalable and Dynamic Environment for Hybrid GUI+CLI AgentsSeptember 4, 2026 · arXiv
- OmegaUse-SOP: SOP Engineering for Professional Computer Use from Human DemonstrationsSeptember 2, 2026 · arXiv
- ASIL: Replacing Screenshot-and-Click with Structured State and Semantic ActionsAugust 27, 2026 · arXiv
- VLAA-GUI: Knowing When to Stop, Recover, and Search, A Modular Framework for GUI AutomationApril 23, 2026 · arXiv
- EE-MCP: Self-Evolving MCP-GUI Agents via Automated Environment Generation and Experience LearningApril 10, 2026 · arXiv
- OpeFlo: Automated UX Evaluation via Simulated Human Web Interaction with GUI GroundingFebruary 25, 2026 · arXiv
- ShowUI-Aloha: Human-Taught GUI AgentJanuary 12, 2026 · arXiv