5 papers
PersonaFactor: Preference Factors with Dynamic Selection for LLM Personalization
Hang Su, Zequn Liu, Jianghan Chao +3
Although users may express different personalization needs across tasks, these task-specific behaviors can reflect shared underlying preference mechanisms. Existing LLM personaliza…
Shared Worlds, Private Minds: Structured Memory for Long-Form Writing as World Creation
Qiuyu Tian, Xiaowen Gu, Hang Su +9
LLM agents that write long-form fiction need an explicit memory of the evolving storyworld to keep new events consistent with established facts. Such memory must keep heterogeneous…
Narrative Knowledge Weaver: Narrative-Centric Retrieval-Augmented Reasoning for Long-Form Text Understanding
Qiuyu Tian, Fengyi Chen, Yiding Li +9
Long-form narrative QA requires reasoning over evolving story worlds rather than isolated passages: answers may depend on earlier goals, changing character states, social relations…
ForeSci: Evaluating LLM Agents for Forward-Looking AI Research Judgment
Qiuyu Tian, Haojie Yin, Yingce Xia +5
AI research often requires decisions before future evidence exists: which bottleneck to attack, which direction to pursue, or where a project should be positioned. We introduce For…
STAGE: A Full-Screenplay Benchmark for Reasoning over Evolving Stories
Qiuyu Tian, Yiding Li, Yingce Xia +9
Movie screenplays are a demanding testbed for long-form narrative understanding, as characters' goals, beliefs, knowledge, and relationships evolve continuously across scenes. Howe…