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

S. Shankar Sastry

2 indexed papers

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

Publications per year

2
26

Top categories

Robotics×2AI×2Systems and Control×1NLP×1ML×1

Frequent co-authors

Haoru Xue2×
Yen-Jen Wang1×
Haozhe Jiang1×
Shuying Deng1×
Weirui Ye1×
Rocky Duan1×

Research Timeline

2026
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.

Reconstruct, Practice, Go Real: Guided Self-Improvement for Embodied Agents

RPG framework improves robot execution systems without updating model weights by identifying manipulation capabilities, constructing practice tasks, and revising system prompts.

Highlighted terms show continued research focus across papers

Papers

cs.ROcs.AIeess.SYEmpiricalRecentOct 1, 2026

Reconstruct, Practice, Go Real: Guided Self-Improvement for Embodied Agents

Yen-Jen Wang, Haozhe Jiang, Shuying Deng, Haoru Xue +6 more

RPG framework improves robot execution systems without updating model weights by identifying manipulation capabilities, constructing practice tasks, and revising system prompts.

View →
cs.ROcs.AIcs.CLEmpirical
Recent
Jul 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 →