按本站收录日期（UTC）归档，不代表事件发生于当天；原公告、聚合源发布与收录时间分别标注。
返回资讯列表arXiv cs.RO ·
Achieving the broad task generalization of embodied models in physical environments remains a central challenge in robot learning. We study this challenge in World Action Models…
原文内容 · 暂无该语言译文arXiv cs.CL ·
Conversational assistants are expected to help people with diverse backgrounds, preferences, and communication styles. Yet evaluations centered on a single cooperative user prov…
原文内容 · 暂无该语言译文arXiv cs.RO ·
LLM-based robotic agent systems can generate programs for robot control, yet their generalization to new tasks often depends on elaborate scaffolding. Expanding their skill repe…
原文内容 · 暂无该语言译文arXiv cs.CL ·
The emergence of writable, cross-session persistent memory in LLM agents introduces a qualitatively different threat landscape from conventional input-centric security concerns,…
原文内容 · 暂无该语言译文
