A deep reinforcement learning system for optimizing bridge maintenance decisions across municipal infrastructure fleets, implementing cross-subsidy budget sharing and cooperative multi-agent learning.

建設の技術基準に関する質問の専門性粒度（細かい/粗い）を96%正確に自動判定し、最適なRAGシステム（ColBERT/Naive）を選択する実用的なAgentic RAGシステムのMVPです。2025年11月に公開された河川砂防ダムの技術基準を対象に４つのRAGシステムを構築し、専門性の粒度が異なる200問の質問に対して、精度と速度を比較した。

This system analyzes bridge repair method recommendation reports generated by AI agents and visualizes the decision-making pathway from damage → deterioration factors → repair methods as a Decision Tree. It aims to "make the thought process visible."

This project applies self-improving (Agentic) clustering with Bayesian Optimization to bridge maintenance data in some Prefecture, Japan, to automatically identify bridge groups with high maintenance priority.

Deep Agentsライブラリのアーキテクチャを活用した、ハーネス構成のRAGシステムです。複数のエージェントが協調動作し、質問の粒度に応じて最適なRAGシステム（Naive RAG / ColBERT RAG）を自動選択します。

Gemma3 RAG benchmark system for Japanese river/dam/erosion control technical standards.

An advanced RAG (Retrieval-Augmented Generation) system using RAPTOR algorithm to hierarchically organize and retrieve lessons from the 2011 Great East Japan Earthquake and Tsunami for educational purposes.

Multimodal RAPTOR for Disaster Documents using ColVBERT & BLIP. Hierarchical retrieval system over 46 tsunami-related PDFs (2378 pages), combining BLIP-based image captioning, ColVBERT embeddings, and GPT-OSS-20b long-context summarization. Optimized for fast multimodal tree construction and disaster knowledge preservation.

This tool applies self-improving (Agentic) clustering to bridge maintenance data in Open data at some Prefecture, Japan, to automatically identify bridge groups with high maintenance priority.