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.
citation dossier
Efficient multi-turn rl for gui agents via decoupled training and adaptive data curation
2Pith papers citing it
3reference links
cs.AItop field · 2 papers
UNVERDICTEDtop verdict bucket · 2 papers
why this work matters in Pith
Pith has found this work in 2 reviewed papers. Its strongest current cluster is cs.AI (2 papers). The largest review-status bucket among citing papers is UNVERDICTED (2 papers). For highly cited works, this page shows a dossier first and a bounded explorer second; it never tries to render every citing paper at once.
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.