This repository is a curated list of academic papers, resources, and models focused on Large Language Models (LLMs) for role-playing with assigned personas. It aims to serve researchers and developers working on character-based AI interactions, multi-agent systems, and persona simulation, providing a comprehensive overview of the field.

How It Works

The project curates a wide range of research, categorizing it into key areas such as Role-Playing, Characters, Demographics, Personalization, Multi-Agents, Anthropomorphic Cognition, and Social Intelligence. It highlights recent advancements, benchmarks, and models, facilitating discovery and understanding of the state-of-the-art in LLM role-playing capabilities.

Quick Start & Requirements

This repository is a curated list and does not have direct installation or execution requirements. It serves as a reference for external resources, papers, and models.

Highlighted Details

• Features a comprehensive survey paper: "From Persona to Personalization: A Survey on Role-Playing Language Agents."
• Includes links to benchmarks like RPBench Leaderboard and models such as Higgs-Llama-3 70B V2.
• Lists numerous papers covering character simulation, persona fidelity, multi-agent role-playing, and personality trait analysis.
• Provides links to relevant blogs and resources for further exploration.

Maintenance & Community

The repository is actively maintained, with recent updates and calls for collaborators. It links to a survey paper and mentions Boson AI as a contributor. Contact information for collaboration is provided.

Licensing & Compatibility

The repository itself is a list of links and does not have a specific license. Individual papers and models linked within the repository will have their own respective licenses.

Limitations & Caveats

The repository's scope is primarily focused on character role-playing and may not cover all related research areas like multi-agent systems or long-context models exhaustively. It is a curated list, and the inclusion of resources is subject to the maintainers' discretion.