EinsiaAI· @EinsiaAI · X·· 7 小时前AI 评分
EmbodiedEvo让智能体在物理世界中进化
编码智能体正在进入物理世界。 零样本只是起点。 如果我们给它们练习机会——并让下一个智能体继承它们学到的经验呢？ EmbodiedEvo：一个 Playground → 可复用的 Skills & Lessons → 未见过的布局。不更新模型权重。 平均分 45.08。成功率 38.95%。 RoboDojo 排行榜第一。 项目：lab.einsia.ai/embodiedevo/ 论文：arxiv.org/abs/2610.18867 Github：github.com/Einsia/EmbodiedEv…
Coding agents are entering the physical world.
Zero-shot is only the starting point.
What if we gave them practice—and let the next agent inherit what they learned?
EmbodiedEvo: one Playground → reusable Skills & Lessons → unseen layouts. No model-weight updates.
45.08 average score. 38.95% success.
#1 on the RoboDojo leaderboard.
Project: lab.einsia.ai/embodiedevo/
Paper: arxiv.org/abs/2610.18867
Github：github.com/Einsia/EmbodiedEv…
来源：EinsiaAI · x.com