Zhan Shu
Papers
2
Total Citations
8
H-Index
2
About
Zhan Shu is an emerging researcher working at the intersection of artificial intelligence, robotics, and large language models (LLMs), with a particular focus on advancing autonomous decision-making and planning capabilities in robotic systems. His work addresses some of the most pressing challenges in deep reinforcement learning (DRL) and sequential task planning, areas where manual design bottlenecks have historically limited scalability and real-world applicability. Among his notable contributions, Shu has pioneered the use of self-refinement mechanisms within LLMs to automate reward function design for deep reinforcement learning in robotics — a breakthrough that reduces the need for labor-intensive human engineering. His ISR-LLM framework further demonstrates how iterative self-refinement can empower language models to tackle complex, long-horizon sequential task planning problems that traditional methods struggle to address effectively. Though early in his citation trajectory, with his 2023 papers already attracting attention from the research community, Shu's work signals a growing recognition of LLM-driven automation as a transformative direction in robotics research. His contributions are particularly valuable for students and researchers exploring how generative AI can be meaningfully integrated into embodied intelligence and autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2