📋 Overview
Investigation into emerging benchmark methodologies for assessing the agentic capabilities of LLMs in gaming scenarios. Developed a Model Context Protocol (MCP) tool for Gomoku (Five-in-a-Row) to evaluate strategic abilities in AI agents.
🛠️ Technologies
⚡ Features
- Model Context Protocol - Standard interface for LLM tools
- Strategic Evaluation - Assesses AI decision-making
- Gomoku Game - Five-in-a-Row game implementation
- Benchmark Tool - Measures agentic capabilities