What I Gained from Interacting with Shogi AI: The Path to 1st Place in Floodgate and My Approach to Distilled Models

Introduction As a practical testing ground for verifying reasoning optimization and model handling, I first touched an OSS shogi software in January 2026. As a result, I reached rank 1 by playing over 200 games with a rating exceeding 4500 on Floodgate (an online shogi server for computer shogi). Since I started programming in December 2025, this was achieved in approximately two months after touching the OSS. This article is not a how-to guide on implementation, but rather discusses what was learned through shogi AI and how it can be applied to LLM research from the perspective of an LLM/RAG researcher. Why Chess AI? In LLM research, one frequently encounters challenges such as reasoning optimization and model selection. However, LLM evaluation can be ambiguous. "Is the answer good?" often involves subjectivity. In contrast, shogi AI has clear wins/losses and ratings, allowing immediate numerical verification of strategy effectiveness. Additionally, skill sets such as CUDA/TensorRT bu