Author

Kohsei Matsutani

h-index 4 View on Semantic Scholar

We have 2 of 7 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Sep 2026

Few-Shot Demonstrations Elicit the Use of In-Context World Representations in LLMs

Large language models (LLMs), when acting as agents, are expected to take observed data in context, infer the latent state space underlying the world, and leverage it for downstream prediction. However, prior work demonstrated that LLMs struggle to use representations learned in context on a graph tracking task, where...

Kohsei Matsutani, Gouki Minegishi, C. Park et al. · 0 citations

#artificial intelligence May 2026

Zipping the Thought: When and How Compressed Reasoning Data Works in LLM Post-Training

A taxonomy of CoT is proposed consisting of Explicit CoT, which outputs all operations without aggregation, Composed CoT, which combines multiple operations into a single step, and Implicit CoT, which omits intermediate operations.

Kohsei Matsutani, Gouki Minegishi, Takeshi Kojima et al. · arXiv.org · 1 citation