Agent S2: A Compositional Generalist-Specialist Framework for Computer Use Agents

Agent S2 is a compositional generalist-specialist framework that splits computer-use responsibilities across specialized and generalist models rather than using a single monolithic agent. Its core methods are Mixture-of-Grounding for precise localization and Proactive Hierarchical Planning for long-horizon control, yielding strong gains on OSWorld, WindowsAgentArena, and AndroidWorld.

• OpenGCUA: Toward a Fully Open Stack for Generalist Computer Use
  October 15, 2026 · arXiv
• OS-Helix: Unifying GUI Interaction and Code Execution in Native Computer-Using Agents
  October 15, 2026 · arXiv
• LEASH: Uncertainty-Aware Weak-to-Strong Escalation and Oversight for Computer-Use Agents
  October 15, 2026 · arXiv
• GUI-HARVEST: Self-Improving GUI Agents through Evidence-Driven Harness Evolution
  October 1, 2026 · arXiv
• HybridCUA: Learning to Orchestrate GUI and CLI for Computer-Use Agents
  September 29, 2026 · arXiv
• RSIAgent: Autonomous Exploration for Recursive Self-improvement in New Environments
  September 14, 2026 · arXiv
• Watch and Learn: Learning to Use Computers from Online Videos
  October 6, 2025 · CVPR 2026
• CoAct-1: Computer-using Multi-Agent System with Coding Actions
  August 5, 2025 · ICLR 2026 (Poster)
• LiteCUA: Computer as MCP Server for Computer-Use Agent on AIOS
  May 24, 2025 · arXiv
• Focused Omni-Modal GUI Agents
  October 19, 2026 · arXiv
• Agent World Model in the Wild: Computer-Use Agent Environment Synthesis
  October 19, 2026 · arXiv
• Iron: Intent-Aligned and Retrospective Dual Learning Framework for Enhancing Generalist Virtual Agents
  August 28, 2026 · arXiv
• Agent Alpha: Tree Search Unifying Generation, Exploration and Evaluation for Computer-Use Agents
  February 3, 2026 · arXiv
• Agentic Reward Modeling: Verifying GUI Agent via Online Proactive Interaction
  January 31, 2026 · arXiv
• BEAP-Agent: Backtrackable Execution and Adaptive Planning for GUI Agents
  January 29, 2026 · arXiv
• LongHorizonUI: A Unified Framework for Robust long-horizon Task Automation of GUI Agent
  January 26, 2026 · ICLR 2026 (Poster)
• From Off-Policy to On-Policy: Enhancing GUI Agents via Bi-level Expert-to-Policy Assimilation
  January 9, 2026 · arXiv
• R-WoM: Retrieval-augmented World Model For Computer-use Agents
  October 13, 2025 · ICLR 2026 (Poster)
• Just Do It!? Computer-Use Agents Exhibit Blind Goal-Directedness
  October 2, 2025 · ICLR 2026 (Poster)
• SheetCopilot: Bringing Software Productivity to the Next Level through Large Language Models
  May 30, 2023 · NeurIPS 2023
• Evolving Agent Interfaces
  October 20, 2026 · arXiv
• VeriCUA: Learning Proactive Verification for Reliable GUI Agent Rewards
  October 19, 2026 · arXiv
• Step-Aligned Script Generation with Verification and Recovery for Web Automation Testing
  October 19, 2026 · arXiv
• CUA-Lite: An Open Platform for Computer Use Agents
  October 19, 2026 · arXiv