Tomoyuki Kagaya
Papers
1
Total Citations
5
H-Index
1
About
Tomoyuki Kagaya is a rising researcher at the forefront of multimodal AI and embodied agent systems. His work centers on enhancing the decision-making and planning capabilities of Large Language Model (LLM) agents, particularly by integrating memory and retrieval mechanisms. In his highly cited 2024 paper, "RAP: Retrieval-Augmented Planning with Contextual Memory for Multimodal LLM Agents," Kagaya introduces a novel framework that enables LLM agents to reflect on past experiences—a core human behavior—to improve current decision-making in complex, real-world domains such as robotics, gaming, and API integration. This work, already garnering 5 citations in a short time, addresses a critical gap in agent autonomy by combining retrieval-augmented generation with contextual memory. Kagaya’s contributions are pivotal for advancing how AI systems learn from and adapt to their environments, moving beyond static, one-shot reasoning. His research promises to unlock more robust, adaptive, and intelligent agents capable of handling dynamic, multimodal tasks, marking him as a key innovator in the next wave of interactive AI.
Research Focus
Key Achievements
Top Papers
- 1