Role-Playing Agents Driven by Large Language Models: Current Status, Challenges, and Future Trends

TL;DR

The paper examines how large language models enable role-playing language agents (RPLAs) that maintain consistent personalities, rational behaviors, and immersive interactions. It analyzes the evolution from rule-based templates to style imitation and then to cognitive, motivation-driven modeling, and it consolidates data construction, annotation, and evaluation frameworks essential for credible RPLAs. Key contributions include synthesizing data sources (novels, scripts, life-like corpora), memory mechanisms (CHARMAP and memory-augmented prompting), and behavioral planning approaches (LIFECHOICE, narrative planning), along with benchmarks such as RoleEval, CharacterEval, RoleBench, and RVBench. It also discusses future directions like dynamic personality evolution, multi-agent narratives, multimodal interaction, and neuroscience-informed design, while addressing data openness and value alignment concerns. This work provides methodological guidance for researchers and practitioners aiming to deploy believable digital characters in entertainment, education, and digital humans.

Abstract

In recent years, with the rapid advancement of large language models (LLMs), role-playing language agents (RPLAs) have emerged as a prominent research focus at the intersection of natural language processing (NLP) and human-computer interaction. This paper systematically reviews the current development and key technologies of RPLAs, delineating the technological evolution from early rule-based template paradigms, through the language style imitation stage, to the cognitive simulation stage centered on personality modeling and memory mechanisms. It summarizes the critical technical pathways supporting high-quality role-playing, including psychological scale-driven character modeling, memory-augmented prompting mechanisms, and motivation-situation-based behavioral decision control. At the data level, the paper further analyzes the methods and challenges of constructing role-specific corpora, focusing on data sources, copyright constraints, and structured annotation processes. In terms of evaluation, it collates multi-dimensional assessment frameworks and benchmark datasets covering role knowledge, personality fidelity, value alignment, and interactive hallucination, while commenting on the advantages and disadvantages of methods such as human evaluation, reward models, and LLM-based scoring. Finally, the paper outlines future development directions of role-playing agents, including personality evolution modeling, multi-agent collaborative narrative, multimodal immersive interaction, and integration with cognitive neuroscience, aiming to provide a systematic perspective and methodological insights for subsequent research.

Figures (1)

• Figure 1: Construction Process of High-Quality Role-Specific Corpora