long-horizon-consistency

This paper introduces NCP-Bench, a benchmark derived from 100 movie synopses for evaluating long-horizon narrative consistency in LLM-based interactive storytelling agents. Experiments show that even strong models like GPT-5.2 struggle to maintain logical consistency, with a 42% survival rate after 20 turns and high fact conflict rates.

NeuWorld is a new interactive video generation system that uses compact neural implicit scene representations and a transformer VAE with diffusion transformer for trajectory-conditioned rendering, achieving long-horizon consistency.