# LLM-Driven NPCs: Cross-Platform Dialogue System for Games and Social Platforms

arXiv: https://arxiv.org/abs/2504.13928 · HTML: https://mlsanity.com/paper/2504.13928/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 10 references that are in the map.
- First posted on arXiv 14 Apr 2025.

## Builds on (most cited first, 5 of 5)

- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [The Rise and Potential of Large Language Model Based Agents: A Survey](https://mlsanity.com/paper/2309.07864/) (2023)
- [DialogBench: Evaluating LLMs as Human-like Dialogue Systems](https://mlsanity.com/paper/2311.01677/) (2023)
- [Player-Driven Emergence in LLM-Driven Game Narrative](https://mlsanity.com/paper/2404.17027/) (2024)
- [PANGeA: Procedural Artificial Narrative using Generative AI for Turn-Based Video Games](https://mlsanity.com/paper/2404.19721/) (2024)

## Built on by (most cited first, 5 of 5)

- [A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense Countermeasures](https://mlsanity.com/paper/2506.19676/) (2025)
- [State-Inference-Based Prompting for Natural Language Trading with Game NPCs](https://mlsanity.com/paper/2507.07203/) (2025)
- [Deflanderization for Game Dialogue: Balancing Character Authenticity with Task Execution in LLM-based NPCs](https://mlsanity.com/paper/2510.13586/) (2025)
- [Aligning Large Language Models with Procedural Rules: An Autoregressive State-Tracking Prompting for In-Game Trading](https://mlsanity.com/paper/2510.25014/) (2025)
- [Systematizing LLM Persona Design: A Four-Quadrant Technical Taxonomy for AI Companion Applications](https://mlsanity.com/paper/2511.02979/) (2025)

## Abstract (arXiv)

NPCs in traditional games are often limited by static dialogue trees and a single platform for interaction. To overcome these constraints, this study presents a prototype system that enables large language model (LLM)-powered NPCs to communicate with players both in the game en vironment (Unity) and on a social platform (Discord). Dialogue logs are stored in a cloud database (LeanCloud), allowing the system to synchronize memory between platforms and keep conversa tions coherent. Our initial experiments show that cross-platform interaction is technically feasible and suggest a solid foundation for future developments such as emotional modeling and persistent memory support.