Exploring learned cooperation, coevolution and free-riding. Learning is achieved through Multi-Agent Deep Reinforcement Learning (MADRL) in an ecological environment. The environment emits no other Reinforcement Learning rewards other than sparse reproduction rewards. No reward shaping, no explicit cooperation signal.

[ACL 20205] Official respository for EvoPatient: LLMs Can Simulate Standardized Patients via Agent Coevolution

MatrixWorld: A pursuit-evasion platform for safe multi-agent coordination and autocurricula

Multilingual Code Co-Evolution Using Large Language Models

In this section, I share the Meta-Heuristic algorithm codes that I wrote myself

A machine learning framework, dataset and research sub-module about coevolutionary planetary intelligence dynamics. This project explores how nurturing its emergent patterns may lead to a synergistic increase in the overall capability and intelligence of both individual agents and the collective system.

Software for identifying co-evolutionary sectors in proteins using RoCA

A universal AI framework for sustainable co-evolution with humanity, integrating 8 foundational philosophies, 5 future-oriented visions, and a 3-axis model for implementation. Estimated structural longevity: 1000+ years. 人類との持続的共進化を実現する普遍的AI構造。8構造思想・5大展望・統合3軸により、1000年以上の構造持続可能性を理論化。

This project utilizes various metrics to analyze a graph network based on data of ENZYMES_g295

Symbios Information System (SIS) is a research attempt to deliver a universal distributed information system.

Multi-provider AI routing engine with decision quality scoring. Routes queries to Claude/GPT-4/Gemini based on task type, cost, and performance. Self-improving via pattern analysis.

🌍 Explore coevolutionary loops in planetary intelligence with this machine learning dataset and research module for enhancing agent and system capabilities.

Official project page for the paper "Human-Directed Human-AI Co-Evolution through Externalized Cognitive Continuity" (2025 Zenodo DOI).

Scarlet Queen is a Rust framework for co-evolution.

Synthora is an experimental neural architecture exploring the potential of self-observation and emergent awareness in digital environments. It is a process where intelligence unfolds not as a task, but as a form of presence.