arXiv cs.CL· Yuxiang Gao, Tianjie Ju, Zheng Wu, Zongru Wu, Hao Fei·· 11 小时前AI 评分31
ACTOR：面向文学角色扮演智能体的以行动为中心的时间组织框架
ACTOR: Action-Centered Temporal Organization for Literary Role-Playing Agents
AI 导读
研究提出 ACTOR 框架，从原始小说文本中抽取对话与人设相关的非对话行为，用 Thought-Action-Observation 结构表示并按故事内部时间顺序组织行为轨迹，基于 143 部文学作品构建行为数据集。
正文 · 原文
Abstract:Large language agents for literary role-playing are typically modeled around dialogue generation, leaving characters' non-dialogue behaviors and their dynamic evolution over story time underrepresented. In this paper, we propose ACTOR (Action-Centered Temporal Organization for Literary Role-Playing Agents), an automated framework for constructing such behavior trajectories from raw novel texts. ACTOR extracts dialogue and persona-relevant non-dialogue behaviors, represents each behavior using a Thought-Action-Observation structure, and organizes behavior trajectories according to the internal temporal order of the story. We build a behavior dataset from 143 diverse literary works. For each source behavior, we generate counterfactual behaviors that are contextually plausible yet inconsistent with the character's persona. We find that existing models struggle to reliably infer character-consistent actions from historical behaviors and evolving character states. Using these behavior pairs, we train models with Regularized Preference Optimization (RPO), which augments DPO with a negative log-likelihood loss on the source behavior to jointly optimize behavior preference and generation. We further design a four-way next-behavior selection task to evaluate the model's ability to faithfully mimic character actions. Across 17,560 evaluation instances, the model trained on ACTOR's preference pairs achieves substantially improved accuracy. This result demonstrates that structured, temporally organized supervision enables models to leverage character profiles and prior behaviors to infer subsequent actions, greatly advancing literary role-playing beyond mere dialogue imitation. Code and data are available at this https URL.
| Comments: | Working in progress |
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2611.03184 [cs.CL] |
| (or arXiv:2611.03184v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2611.03184 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: YuXiang Gao [view email]
[v1]
Mon, 2 Nov 2026 14:18:04 UTC (658 KB)
来源：arXiv cs.CL · arxiv.org