Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Guanzhi Wang

Guanzhi Wang

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

Robotics×2AI×2NLP×1ML×1Multiagent×1

Frequent co-authors

Letian Fu2×
Yuke Zhu2×
Linxi "Jim" Fan2×
Ken Goldberg2×
Kaiyuan Chen1×
Shuangyu Xie1×

Research Timeline

2026
ASPIRE: Agentic /Skills Discovery for Robotics

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.

GaP: A Graph-as-Policy Multi-Agent Self-Learning Harness For Variational Automation 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.

Highlighted terms show continued research focus across papers

Papers

cs.ROcs.AIcs.CLEmpiricalRecentJul 6, 2026

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…

View →
cs.ROcs.AIcs.MAEmpirical
Recent
Jun 30, 2026

ASPIRE: Agentic /Skills Discovery for Robotics

Runyu Lu, Yubo Wu, Ethan Kou, Letian Fu +10 more

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…

View →