Explore, Execute, Evolve: A Skill Acquisition and Reuse Loop for Embodied Agents

原文：Explore, Execute, Evolve: A Skill Acquisition and Reuse Loop for Embodied Agents

作者：Sicheng Xie, Yitong Chen, Haidong Cao, Shunlin Lu, Zuxuan Wu, Yu-Gang Jiang

来源：arXiv cs.RO（机器人）

正文

Computer Science > Robotics

arXiv:2609.37810v1 (cs)

[Submitted on 29 Sep 2026]

Title:Explore, Execute, Evolve: A Skill Acquisition and Reuse Loop for Embodied Agents

Authors:Sicheng Xie, Yitong Chen, Haidong Cao, Shunlin Lu, Zuxuan Wu, Yu-Gang Jiang

View a PDF of the paper titled Explore, Execute, Evolve: A Skill Acquisition and Reuse Loop for Embodied Agents, by Sicheng Xie and 5 other authors

View PDF

HTML (experimental)

Abstract:Vision-language-action and world-action models have demonstrated impressive capabilities in robotics, yet generalization to unseen tasks remains challenging. More recently, general-purpose multimodal agents have shown great potential for zero-shot robotic task solving. However, they often incur high execution costs by reasoning and exploring the physical world from scratch. To reduce these costs, we introduce RoboSkill, a framework that connects skill acquisition and reuse through an Explore, Execute, Evolve loop. Within this loop, the agent explores to gather task-relevant information, executes tasks while adapting to feedback, and evolves its skill library based on execution records. It then reuses these skills to guide exploration and execution in the next cycle, closing the loop. To improve loop efficiency, we complement vision with tactile feedback to reduce uncertainty during physical interaction. We further augment textual guidance with reusable code to reduce reasoning overhead during skill reuse. On LIBERO-10, RoboSkill improves first-episode success rates by 12.5–25.0 percentage points and reduces average runtime by 7.6–72.4% across four agents. On real robots, it improves success rates by 8.3 percentage points and reduces average runtime for successful trials by at least 14.4%.

Subjects:

Robotics (cs.RO); Artificial Intelligence (cs.AI)

Cite as:

arXiv:2609.37810 [cs.RO]

(or

arXiv:2609.37810v1 [cs.RO] for this version)

https://doi.org/10.48550/arXiv.2609.37810

Focus to learn more

arXiv-issued DOI via DataCite (pending registration)

主题

机器人 · 人工智能

由「前沿雷达」于 2026-09-29 采集。正文取自原文页面，已保留出处链接。标题与正文版权归原作者所有。