Agent S: An Open Agentic Framework that Uses Computers Like a Human
Saaket Agashe , Jiuzhou Han , Shuyu Gan , Jiachen Yang , Ang Li , Xin Eric Wang
- 🏛 Institutions
- Simular Research
- 📅 Date
- October 10, 2024
- 📑 Publisher
- ICLR 2025 (Poster)
- 💻 Env
- Desktop
- 🔑 Keywords
TLDR
Agent S is an open computer-use framework built around an Agent-Computer Interface plus experience-augmented hierarchical planning that combines online web knowledge with narrative and episodic memory. The paper reports state-of-the-art OSWorld results and shows transfer to WindowsAgentArena without explicit adaptation.
Related papers (24)
- 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
- ShowUI-Aloha: Human-Taught GUI AgentJanuary 12, 2026 · arXiv
- Surfer 2: The Next Generation of Cross-Platform Computer Use AgentsOctober 22, 2025 · arXiv
- BIMgent: Towards Autonomous Building Modeling via Computer-use AgentsJune 8, 2025 · ICML 2025 Workshop on Computer-use Agents
- LiteCUA: Computer as MCP Server for Computer-Use Agent on AIOSMay 24, 2025 · arXiv
- UFO2: The Desktop AgentOSApril 20, 2025 · arXiv
- WorldGUI: An Interactive Benchmark for Desktop GUI Automation from Any Starting PointFebruary 12, 2025 · arXiv
- PC Agent: While You Sleep, AI Works -- A Cognitive Journey into Digital WorldDecember 23, 2024 · arXiv
- AgentStore: Scalable Integration of Heterogeneous Agents As Specialized Generalist Computer AssistantOctober 24, 2024 · Findings of ACL 2025
- AXIS: Efficient Human-Agent-Computer Interaction with API-First LLM-Based AgentsSeptember 26, 2024 · ACL 2025
- OS-Copilot: Towards Generalist Computer Agents with Self-ImprovementFebruary 12, 2024 · LLMAgents @ ICLR 2024
- Synapse: Trajectory-as-Exemplar Prompting with Memory for Computer ControlJune 13, 2023 · ICLR 2024 (Poster)
- MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent ResearchMay 25, 2026 · arXiv
- ClawGUI: A Unified Framework for Training, Evaluating, and Deploying GUI AgentsApril 13, 2026 · arXiv
- Why Do LLM-based Web Agents Fail? A Hierarchical Planning PerspectiveMarch 15, 2026 · arXiv
- OpeFlo: Automated UX Evaluation via Simulated Human Web Interaction with GUI GroundingFebruary 25, 2026 · arXiv
- LongHorizonUI: A Unified Framework for Robust long-horizon Task Automation of GUI AgentJanuary 26, 2026 · ICLR 2026 (Poster)
- GraphPilot: GUI Task Automation with One-Step LLM Reasoning Powered by Knowledge GraphJanuary 24, 2026 · Journal of Intelligent Computing and Networking
- ColorBrowserAgent: Complex Long-Horizon Browser Agent with Adaptive Knowledge EvolutionJanuary 12, 2026 · arXiv
- GUITester: Enabling GUI Agents for Exploratory Defect DiscoveryJanuary 8, 2026 · arXiv
- WebATLAS: An LLM Agent with Experience-Driven Memory and Action SimulationOctober 26, 2025 · NeurIPS 2025 Workshop on Language Agents and World Models
- PolySkill: Learning Generalizable Skills Through Polymorphic AbstractionOctober 17, 2025 · arXiv
- CORE: Reducing UI Exposure in Mobile Agents via Collaboration Between Cloud and Local LLMsOctober 17, 2025 · NeurIPS 2025 (Poster)