Thong Jing Yuan
Papers
1
Total Citations
5
H-Index
1
About
Thong Jing Yuan is a rising researcher at the forefront of multimodal AI and autonomous agent systems. His work centers on enhancing Large Language Models (LLMs) with advanced reasoning, planning, and memory capabilities, enabling them to tackle complex, real-world decision-making tasks in robotics, gaming, and API integration. His most-cited paper, "RAP: Retrieval-Augmented Planning with Contextual Memory for Multimodal LLM Agents" (2024, 5 citations), introduces a groundbreaking framework that empowers LLM agents to dynamically retrieve and reflect upon past experiences—mimicking innate human memory—to improve current decision-making. This work addresses a critical limitation in AI: the inability to leverage historical context for adaptive planning. Though early in his career, Thong’s contributions are already shaping the next generation of intelligent, context-aware agents. His research promises to bridge the gap between static AI models and truly autonomous systems capable of learning from their own histories.
Research Focus
Key Achievements
Top Papers
- 1