Guanzhi Wang
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
ASPIRE is a continual learning system that autonomously writes and refines robot control programs in a code-as-policy paradigm, discovering transferable skills and surpassing prior methods on various manipulation tasks.
The paper introduces Graph-as-Policy (GaP), a multi-agent coding harness for Variational Automation tasks that generates directed computation graphs and improves success rates and throughput through internal simulation.
Papers
GaP: A Graph-as-Policy Multi-Agent Self-Learning Harness For Variational Automation Tasks
Kaiyuan Chen, Shuangyu Xie, Letian Fu, Justin Yu +20 more
The paper introduces Graph-as-Policy (GaP), a multi-agent coding harness for Variational Automation tasks that generates directed computation graphs and improves success rates and throughput through i…