Tag
This paper presents AutoWorldBuilder, a multi-agent LLM system for automated fictional worldbuilding that addresses context explosion, creative diversity, and quality assurance through hierarchical context compression, DAG-based scheduling, and iterative review, achieving 95% success rate and generating 56–103 self-consistent concepts per world.
VideoKR introduces a large-scale video reasoning dataset and benchmark designed to enhance knowledge-intensive video understanding through expert-domain content and human-in-the-loop example generation. The dataset contains 315K video reasoning examples over 145K expert-domain videos.
Proposes AMATA, a multi-agent trajectory alignment framework for knowledge-intensive question answering that introduces intra-trajectory preference learning and inter-agent dependency learning to improve factual grounding and interpretability, outperforming baselines on five benchmarks.