I am a researcher at STAIR Lab , Chiba Institute of Technology. My research focuses on understanding and advancing the reasoning capabilities of large language models and building more capable AI agents.
I am particularly interested in how LLMs perform complex reasoning tasks, including mathematical problem-solving, logical inference, and multi-step planning. My work explores novel architectures and training methodologies to enhance these capabilities.
Beyond reasoning, I investigate the design and implementation of autonomous agents that can effectively interact with their environment, use tools, and accomplish complex goals through structured planning and execution.
Research Interests
LLM Reasoning
Investigating the mechanisms behind chain-of-thought reasoning, mathematical problem-solving, and logical inference in large language models.
AI Agents
Designing autonomous agents capable of tool use, multi-step planning, and effective interaction with complex environments.
Knowledge Representation
Exploring how language models encode and retrieve factual knowledge, and methods for improving knowledge consistency.
Publications
Coming soon.
Contact
Affiliation
STAIR Lab
Chiba Institute of Technology