EvoCUA-1.5: Online RL Framework for Multi-turn Computer-Use Agents

Jul 14, 2026

EvoCUA-1.5 introduces online reinforcement learning for computer-use agents, addressing challenges such as sparse rewards and variable-length trajectories. It achieves 63.2% success on OSWorld-Verified, outperforming comparable 32B/35B-scale open-weight baselines.

Why it matters: This work provides a practical framework for scaling online RL in multi-turn computer-use agents, improving training stability and performance.

Full story at: arXiv AI/ML ↗