Nemobot Games: Crafting Strategic AI Gaming Agents for Interactive Learning with Large Language Models

2026-04-23

AI Summary

This work proposes Nemobot, an interactive agent development framework grounded in large language models (LLMs), designed to construct agents capable of autonomously evolving strategies, adapting across diverse game genres, and synergistically integrating human creativity with AI-driven reasoning. For the first time, the framework unifies Shannon’s game taxonomy—encompassing lexical, solvable, heuristic, and learning-based games—with LLMs, leveraging tool-augmented generation, fine-tuning, reinforcement learning, human feedback (RLHF), self-critique, and imitation learning to enable adaptive strategy generation, self-explanation, and self-programming. Experimental results demonstrate that Nemobot efficiently produces interpretable strategies across all four game categories and validates the feasibility of AI self-programming within interactive environments.

Technology Category

• Humans and AI: Game Design — Procedural Content Generation & Storytelling
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Multiagent Systems: Adversarial Agents

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Uses of LLMs and GenAI for marketplace design, bidding, and strategic interactions
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

This paper introduces a new paradigm for AI game programming, leveraging large language models (LLMs) to extend and operationalize Claude Shannon's taxonomy of game-playing machines. Central to this paradigm is Nemobot, an interactive agentic engineering environment that enables users to create, customize, and deploy LLM-powered game agents while actively engaging with AI-driven strategies. The LLM-based chatbot, integrated within Nemobot, demonstrates its capabilities across four distinct classes of games. For dictionary-based games, it compresses state-action mappings into efficient, generalized models for rapid adaptability. In rigorously solvable games, it employs mathematical reasoning to compute optimal strategies and generates human-readable explanations for its decisions. For heuristic-based games, it synthesizes strategies by combining insights from classical minimax algorithms (see, e.g., shannon1950chess) with crowd-sourced data. Finally, in learning-based games, it utilizes reinforcement learning with human feedback and self-critique to iteratively refine strategies through trial-and-error and imitation learning. Nemobot amplifies this framework by offering a programmable environment where users can experiment with tool-augmented generation and fine-tuning of strategic game agents. From strategic games to role-playing games, Nemobot demonstrates how AI agents can achieve a form of self-programming by integrating crowdsourced learning and human creativity to iteratively refine their own logic. This represents a step toward the long-term goal of self-programming AI.

Problem

• strategic AI
• interactive learning
• large language models
• game-playing agents
• self-programming AI

Innovation

• Large Language Models
• Self-programming AI
• Strategic Game Agents
• Human-in-the-loop Learning
• Tool-augmented Generation