From Persona to Personalization: A Survey on Role-Playing Language Agents

arXiv:2404.18231v1 Announce Type: new
Abstract: Recent advancements in large language models (LLMs) have significantly boosted the rise of Role-Playing Language Agents (RPLAs), i.e., specialized AI systems designed to simulate assigned personas. By harnessing multiple advanced abilities of LLMs, including in-context learning, instruction following, and social intelligence, RPLAs achieve a remarkable sense of human likeness and vivid role-playing performance. RPLAs can mimic a wide range of personas, ranging from historical figures and fictional characters to real-life individuals. Consequently, they have catalyzed …

abstract advanced agents ai systems arxiv context cs.ai cs.cl in-context learning intelligence language language models large language large language models llms multiple personalization personas playing role social specialized ai survey systems type