# Open Role-Playing with Delta-Engines

arXiv: https://arxiv.org/abs/2408.05842 · HTML: https://mlsanity.com/paper/2408.05842/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 36 references that are in the map.
- First posted on arXiv 11 Aug 2024.

## Builds on (most cited first, 22 of 22)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [Genie: Generative Interactive Environments](https://mlsanity.com/paper/2402.15391/) (2024)
- [MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge](https://mlsanity.com/paper/2206.08853/) (2022)
- [The Curse of Recursion: Training on Generated Data Makes Models Forget](https://mlsanity.com/paper/2305.17493/) (2023)
- [Generate rather than Retrieve: Large Language Models are Strong Context Generators](https://mlsanity.com/paper/2209.10063/) (2022)
- [Role-Play with Large Language Models](https://mlsanity.com/paper/2305.16367/) (2023)
- [Exploring Large Language Models for Communication Games: An Empirical Study on Werewolf](https://mlsanity.com/paper/2309.04658/) (2023)
- [RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models](https://mlsanity.com/paper/2310.00746/) (2023)
- [Procedural Content Generation via Machine Learning (PCGML)](https://mlsanity.com/paper/1702.00539/) (2017)
- [Designing Creative AI Partners with COFI: A Framework for Modeling Interaction in Human-AI Co-Creative Systems](https://mlsanity.com/paper/2204.07666/) (2022)
- [From Role-Play to Drama-Interaction: An LLM Solution](https://mlsanity.com/paper/2405.14231/) (2024)
- [PokeLLMon: A Human-Parity Agent for Pokemon Battles with Large Language Models](https://mlsanity.com/paper/2402.01118/) (2024)
- [GAVEL: Generating Games Via Evolution and Language Models](https://mlsanity.com/paper/2407.09388/) (2024)
- [ByteSized32: A Corpus and Challenge Task for Generating Task-Specific World Models Expressed as Text Games](https://mlsanity.com/paper/2305.14879/) (2023)
- [Large Language Models Fall Short: Understanding Complex Relationships in Detective Narratives](https://mlsanity.com/paper/2402.11051/) (2024)
- [NarrativePlay: Interactive Narrative Understanding](https://mlsanity.com/paper/2310.01459/) (2023)
- [Instruction-Driven Game Engines on Large Language Models](https://mlsanity.com/paper/2404.00276/) (2024)

## Built on by (most cited first, 1 of 1)

- [Instruction-Driven Game Engine: A Poker Case Study](https://mlsanity.com/paper/2410.13441/) (2024)

## Abstract (arXiv)

Game roles can be reflections of personas from a parallel world. In this paper, we propose a new style of game-play to bridge self-expression and role-playing: open role-playing games (ORPGs), where players are allowed to craft and embody their unique characters in the game world. Our vision is that, in the real world, we are individually similar when we are born, but we grow into unique ones as a result of the strongly different choices we make afterward. Therefore, in an ORPG, we empower players with freedom to decide their own growing curves through natural language inputs, ultimately becoming unique characters. To technically do this, we propose a special engine called Delta-Engine. This engine is not a traditional game engine used for game development, but serves as an in-game module to provide new game-play experiences. A delta-engine consists of two components, a base engine and a neural proxy. The base engine programs the prototype of the character as well as the foundational settings of the game; the neural proxy is an LLM, which realizes the character growth by generating new code snippets on the base engine incrementally. In this paper, we self-develop a specific ORPG based on delta-engines. It is adapted from the popular animated series ``Pok'emon''. We present our efforts in generating out-of-domain and interesting role data in the development process as well as accessing the performance of a delta-engine. While the empirical results in this work are specific, we aim for them to provide general insights for future games.