4 papers
Multi-Persona Debate System for Automated Scientific Hypothesis Generation
Jaeha Oh, Byungchan Kim, Ju Li +2
Modern scientific discovery is bottlenecked not by data scarcity, but by the inability to synthesize fragmented knowledge into actionable hypotheses. This challenge is especially a…
Agent-as-Judge for Factual Summarization of Long Narratives
Yeonseok Jeong, Minsoo Kim, Seung-won Hwang +1
Large Language Models (LLMs) have demonstrated near-human performance in summarization tasks based on traditional metrics such as ROUGE and BERTScore. However, these metrics do not…
NexusSum: Hierarchical LLM Agents for Long-Form Narrative Summarization
Hyuntak Kim, Byung-Hak Kim
Summarizing long-form narratives--such as books, movies, and TV scripts--requires capturing intricate plotlines, character interactions, and thematic coherence, a task that remains…
CREFT: Sequential Multi-Agent LLM for Character Relation Extraction
Ye Eun Chun, Taeyoon Hwang, Seung-won Hwang +1
Understanding complex character relations is crucial for narrative analysis and efficient script evaluation, yet existing extraction methods often fail to handle long-form narrativ…