TL;DR: ATAS is a world-state-centric framework that helps AI video generators keep "the same place" and "the same event" consistent across multiple separate shots. Title: Any Time, Any Space: A World-State-Centric Framework for Agentic Video Generation URL: Key points 🗺️ Keeps scene memory (static spatial structure) and event memory (dynamic happenings) as two separate, persistent stores 🎬 Recursively compiles a screenplay into shot requests tagged with location, camera, and time ✅ Only validated observations update the world state, so a failed shot's errors don't propagate into later ones 📈 Achieves the top aggregate score across four different video-generation backbones 🧪 Hits a PSNR-C of 15.968 on spatial revisits and an event-identity score of 0.750 on recapture tasks 🙋 Wins highest human ratings on all six criteria, including 4.40/5.0 for script faithfulness and 4.22/5.0 for character consistency I appreciate that the paper is upfront about the trade-off: per-story runtime grows roughly 1.25x in exchange for that consistency. #VideoGeneration# #AIAgents#