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.
Efficient multi-turn rl for gui agents via decoupled training and adaptive data curation
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.AI 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
An exploration-aware policy optimization method lets LLM agents explore selectively via a variational-inference reward and action grouping, yielding consistent gains on text and GUI agent benchmarks.
citing papers explorer
-
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.
-
Learning to Explore: Scaling Agentic Reasoning via Exploration-Aware Policy Optimization
An exploration-aware policy optimization method lets LLM agents explore selectively via a variational-inference reward and action grouping, yielding consistent gains on text and GUI agent benchmarks.