EvoCUA-1.5: Online Reinforcement Learning for Multi-turn Computer-Use Agents
英文标题：EvoCUA-1.5: Online Reinforcement Learning for Multi-turn Computer-Use Agents
arXiv:2607.09773v1 Announce Type: new Abstract: Computer-use agents must solve long-horizon tasks through repeated interaction with partially observable, multimodal desktop environments. Although imitation learning and offline trajectory refinement provide strong priors, static traces cannot cover
打开原文相关 4.8 · 机会 1
2.6 KB
2.1 KB
483 B
612 B
380 B
9.1 KB
32.7 KB
22.8 KB
24.2 KB
34.7 KB
中文
arXiv:2607.09773v1 Announce Type: new Abstract: Computer-use agents must solve long-horizon tasks through repeated interaction with partially observable, multimodal desktop environments. Although imitation learning and offline trajectory refinement provide strong priors, static traces cannot cover
中文全文翻译正在补齐，可先查看下方英文原文。
English / 原文
BibTeX formatted citation
×