Skip to content
Source
arXiv Robotics — research abstracts· He Zhu, Lusen Zhao, Kwan Man Cheng, Su Li, Katerina Fragkiadaki·· 4 days agoEditorial score63

SkillWeaver: Agentic Exploration over Neural Interaction Skills for Scalable Robot Data Generation

SkillWeaver: Agentic Exploration over Neural Interaction Skills for Scalable Robot Data Generation

Summary

SkillWeaver is a framework that autonomously generates robot experience by exploring over Neural Interaction Skills (NIS), which are reusable, parameterized, closed-loop policies. It enables the agent to discover successful long-horizon behaviors through verifier-guided tree search, improving generalization across novel objects, tasks, and environments.

Evidence and limits

Published automatically after robotics and source-evidence checks; no manual editorial approval is recorded. Source assertions are not independently verified. Missing information remains not reported.

Environment:
SimulationSource E1
Control:
Reported autonomousSource E1
Data origin:
Not reported
Source excerpts and review record

No manual editorial approval recorded.

Original source quotation: “We introduce SkillWeaver, an agentic framework that autonomously generates robot experience by exploring over Neural Interaction Skills (NIS): reusable, parameterized, closed-loop policies that expose learned physical interaction capabilities to a reasoning agent.”

Source E1

Source：arXiv Robotics — research abstracts · arxiv.org

#Research#Robot policies#Reinforcement learning#Sim-to-real#Google DeepMind#NVIDIA