在角色中思考：利用角色感知推理推进角色扮演智能体
Thinking in Character: Advancing Role-Playing Agents with Role-Aware Reasoning
AI总结：
本文提出角色感知推理（RAR）方法，通过角色身份激活和推理风格优化两个阶段，解决角色扮演智能体中的注意力转移与风格漂移问题，从而显著提升其角色一致性和表现。
摘要：
大语言模型（LLMs）的进步激发了人们对角色扮演智能体（RPAs）在情感陪伴和虚拟交互等应用中的浓厚兴趣。然而，现有的角色扮演智能体通常建立在显式对话数据之上，缺乏深层的、类人的内部思维过程，导致知识和风格表达流于表面。尽管大型推理模型（LRMs）可用于模拟角色思维，但其直接应用受到注意力转移（即角色扮演智能体忘记自身角色）和风格漂移（即推理过于正式和僵化，而非与角色一致的推理）的阻碍。为解决这些挑战，本文提出了一种新颖的角色感知推理（Role-Aware Reasoning，RAR）方法，该方法包含两个重要阶段：角色身份激活（Role Identity Activation，RIA）和推理风格优化（Reasoning Style Optimization，RSO）。RIA在推理过程中利用角色档案显式引导模型，以对抗注意力转移；随后RSO通过大型推理模型蒸馏使推理风格与角色和场景对齐，以缓解风格漂移。大量实验表明，所提出的RAR通过有效解决注意力转移和风格漂移问题，显著提升了角色扮演智能体的性能。
英文摘要：
The advancement of Large Language Models (LLMs) has spurred significant interest in Role-Playing Agents (RPAs) for applications such as emotional companionship and virtual interaction. However, recent RPAs are often built on explicit dialogue data, lacking deep, human-like internal thought processes, resulting in superficial knowledge and style expression. While Large Reasoning Models (LRMs) can be employed to simulate character thought, their direct application is hindered by attention diversion (i.e., RPAs forget their role) and style drift (i.e., overly formal and rigid reasoning rather than character-consistent reasoning). To address these challenges, this paper introduces a novel Role-Aware Reasoning (RAR) method, which consists of two important stages: Role Identity Activation (RIA) and Reasoning Style Optimization (RSO). RIA explicitly guides the model with character profiles during reasoning to counteract attention diversion, and then RSO aligns reasoning style with the character and scene via LRM distillation to mitigate style drift. Extensive experiments demonstrate that the proposed RAR significantly enhances the performance of RPAs by effectively addressing attention diversion and style drift.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
