Android Coach improves online agent training efficiency by enabling multiple actions per state via a critic-based coach, process reward model, and group-wise advantage estimation, delivering 7.5-8.3% success rate gains and 1.4x efficiency over PPO/GRPO baselines.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
A modular step-level cascade uses Stuck and Milestone monitors to switch between small and large policies in computer-use agents, turning uniform expensive inference into on-demand allocation.
citing papers explorer
-
Android Coach: Improve Online Agentic Training Efficiency with Single State Multiple Actions
Android Coach improves online agent training efficiency by enabling multiple actions per state via a critic-based coach, process reward model, and group-wise advantage estimation, delivering 7.5-8.3% success rate gains and 1.4x efficiency over PPO/GRPO baselines.
-
Step-level Optimization for Efficient Computer-use Agents
A modular step-level cascade uses Stuck and Milestone monitors to switch between small and large policies in computer-use agents, turning uniform expensive inference into on-demand allocation.