用四个核心概念构建角色，让AI扮演更真实有深度。
Operation Veja: Fixing Fundamental Concepts Missing from Modern Roleplaying Training Paradigms
- 提出VEJA框架，聚焦角色的价值、经历、判断和能力
- 实验证明人工标注的VEJA数据比合成数据质量更高
- 适合想提升角色扮演真实感的研究者与开发者
现代角色扮演模型虽日益复杂，却始终难以呈现可信、吸引人的角色。我们指出，这一问题源于训练范式忽视了角色内在世界的动态互动。当前方法如检索增强生成（RAG）、基于事实的提示、文献学习和合成数据生成，在建模人类互动中常见的权衡与价值冲突方面存在系统性局限。本文识别出塑造角色真实性的四大核心概念：价值观（Values）、经历（Experiences）、判断（Judgments）与能力（Abilities），统称为VEJA。我们提出以VEJA为指导的数据构建新范式。通过对比人工精心标注的VEJA数据集与最先进的合成数据基线，我们开展了一项试点研究。使用大模型作为评判标准，结果揭示显著质量差距，表明角色扮演智能体若要具备真正深度与叙事连贯性，必须转向以概念为基础的数据构建方式。完整数据集已开源：https://github.com/HyouinKyoumaIRL/Operation-Veja
原文摘要 · Abstract (English)
Modern roleplaying models are increasingly sophisticated, yet they consistently struggle to capture the essence of believable, engaging characters. We argue this failure stems from training paradigms that overlook the dynamic interplay of a character's internal world. Current approaches, including Retrieval-Augmented Generation (RAG), fact-based priming, literature-based learning, and synthetic data generation, exhibit recurring limitations in modeling the deliberative, value-conflicted reasoning that defines human interaction. In this paper, we identify four core concepts essential for character authenticity: Values, Experiences, Judgments, and Abilities (VEJA). We propose the VEJA framework as a new paradigm for data curation that addresses these systemic limitations. To illustrate the qualitative ceiling enabled by our framework, we present a pilot study comparing a manually curated, VEJA-grounded dataset against a state-of-the-art synthetic baseline. Using an LLM-as-judge evaluation, our findings demonstrate a significant quality gap, suggesting that a shift toward conceptually grounded data curation, as embodied by VEJA, is necessary for creating roleplaying agents with genuine depth and narrative continuity. The full dataset is available at https://github.com/HyouinKyoumaIRL/Operation-Veja
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。