# ArcANE： 角色扮演语言智能体能否在正确时机保持角色？

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-06-04 08:00
- AIHOT 分数：59
- AIHOT 链接：https://aihot.virxact.com/items/cmq0dttfu05aqsltrexhie6xh
- 原文链接：https://arxiv.org/abs/2606.05553

## AI 摘要

现有基准仅评测角色扮演语言智能体（RPLA）对给定章节的事实回忆，未检验其回应是否贴合角色心理发展轨迹，尤其当场景超出原著文本时。ArcANE 是自动构建的基准，覆盖17部小说和80个主角，利用角色弧线将叙事沿心理轴分段，并为每个阶段提出相同场景（含原著内与外）。在6个模型和6种上下文模式下，使用角色弧线作为条件均优于其他策略，在原著外场景（检索无法获取信息）上差距最大。进一步微调开源权重模型得 ArcANE-8B/32B，在原著外场景上扩大了弧线优势。

## 正文

Role-playing language agents (RPLAs) should play characters whose values and behavior evolve as the story progresses, not maintain a fixed persona. Existing benchmarks measure factual recall at a given chapter, not whether responses align with the character's psychological trajectory, especially in scenarios the source text never explores. We introduce ArcANE (Arc-Aware Narrative Evaluation), an automatically constructed benchmark spanning 17 novels and 80 principal characters. A Character Arc segments the narrative into phases along a psychological axis, and each probe poses the same scenario across phases, spanning both situations within the source text and situations beyond it. Across six models and six context modes, conditioning on the Character Arc tops every other context strategy on every model, and the gap is largest on scenarios outside the source text where retrieval has nothing to find. We further fine-tune open-weight models on the same data to obtain ArcANE-8B/32B, which widen the Arc advantage even more on scenarios outside the source text.