Generative world models for autonomous driving face two unresolved tensions: heterogeneous control injection, where free-form language, HD-maps, trajectories, and camera poses reside in incompatible representational spaces, and post-hoc cross-view fusion, where per-camera latents fail to encode global 3-D geometry. We trace both to a single root cause: the absence of a shared symbolic interlingua aligning language, geometry, and pixels at the latent-token level. We present DRIVE-CHOREO, an LLM-choreographed multi-agent world model that recasts controllable multi-view video generation as latent choreography. Three Qwen2.5-VL agents - a Director parsing user intent into a structured WorldScript, a Cartographer grounding it into spatially-anchored layout tokens, and an Auditor feeding cross-view critiques back as auxiliary supervision - jointly author a single position-aware token sequence. This sequence is co-compressed with the multi-view video via a view-time permutation that enforces inter-camera geometry within the convolutional receptive field of a 3-D VAE. On nuScenes, DRIVE-CHOREO sets new state-of-the-art multi-view consistency and BEV mAP (21.6) with competitive FVD (45.7); a detector trained purely on our synthetic data gains +2.4 NDS on the real validation split, validating downstream utility.

翻译：自动驾驶生成式世界模型面临两个未解决的核心张力：异构控制注入（自由形式语言、高精地图、轨迹与相机位姿容纳于不兼容的表示空间）与后验式跨视角融合（单视角编码潜在变量无法编码全局三维几何）。我们将两者归因于同一根本原因：在潜在令牌层面缺乏对齐语言、几何与像素的共享符号中间语。本文提出DRIVE-CHOREO——一种由LLM编排的多智能体世界模型，将可控多视角视频生成重构为潜在编排任务。三个Qwen2.5-VL智能体（解析用户意图至结构化WorldScript的导演智能体、将意图具象化为空间锚定布局令牌的地图制作者智能体、以及将跨视角批评反馈为辅助监督的审核智能体）共同撰写单一位置感知令牌序列。该序列通过视图-时间置换与多视角视频联合压缩，在3D VAE卷积感受野内强制施加跨相机几何约束。在nuScenes数据集上，DRIVE-CHOREO以竞争性FVD（45.7）刷新多视角一致性与BEV mAP（21.6）新纪录；完全基于合成数据训练的检测器在真实验证集上获得+2.4 NDS增益，验证了下游实用性。