A self-evolving MCP-GUI agent system with automated environment generation and an experience bank achieves up to 77.8% pass rates by matching distillation or experience augmentation to task type across three desktop applications.
Osworld-mcp: Benchmarking mcp tool invocation in computer-use agents
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
dataset 1
citation-polarity summary
fields
cs.AI 4years
2026 4verdicts
UNVERDICTED 4roles
dataset 1polarities
use dataset 1representative citing papers
ToolCUA introduces a trajectory scaling pipeline and staged RL to optimize GUI-tool switching, reaching 46.85% accuracy on OSWorld-MCP for a 66% relative gain over baseline.
MM-ToolBench introduces 100 closed-loop multimodal tasks across two domains with 27 MCP servers and 324 tools, where agents must execute, inspect artifacts, and revise before final output.
The paper delivers the first comprehensive overview of RL for GUI agents, organizing methods into offline, online, and hybrid strategies while analyzing trends in rewards, efficiency, and deliberation to outline a future roadmap.
citing papers explorer
-
EE-MCP: Self-Evolving MCP-GUI Agents via Automated Environment Generation and Experience Learning
A self-evolving MCP-GUI agent system with automated environment generation and an experience bank achieves up to 77.8% pass rates by matching distillation or experience augmentation to task type across three desktop applications.
-
ToolCUA: Towards Optimal GUI-Tool Path Orchestration for Computer Use Agents
ToolCUA introduces a trajectory scaling pipeline and staged RL to optimize GUI-tool switching, reaching 46.85% accuracy on OSWorld-MCP for a 66% relative gain over baseline.
-
TOBench: A Task-Oriented Omni-Modal Benchmark for Real-World Tool-Using Agents
MM-ToolBench introduces 100 closed-loop multimodal tasks across two domains with 27 MCP servers and 324 tools, where agents must execute, inspect artifacts, and revise before final output.
-
GUI Agents with Reinforcement Learning: Toward Digital Inhabitants
The paper delivers the first comprehensive overview of RL for GUI agents, organizing methods into offline, online, and hybrid strategies while analyzing trends in rewards, efficiency, and deliberation to outline a future roadmap.