Agentic World Action Models

近期世界动作模型能为机器人操作提供视觉前瞻与未来预测，却缺少组合式技能复用机制。智能体机器人将代码规划和推理与可复用技能结合，但往往缺乏物理动力学层面的预测支撑。本文提出 AW-0，将代码规划与联合视频、动作预测整合为智能体世界动作模型框架。

模型在统一的混合 Transformer 架构中，把代码、未来视频和机器人动作建模为三个耦合生成流。代码专家产生参数化技能过程与控制逻辑，视频和动作专家分别产生未来视觉状态与底层运动指令。

代码承担两种互补作用：在世界模型内部组织多步预测和控制，并把技能表示为可供后续智能体执行的可复用程序。论文还提出自动整理流程，为机器人和人类视频轨迹标注对齐程序，将反复出现的操作整理为技能库。

RoboTwin 2.0 与真实双臂操作评测显示，相比 VLA 和 WAM 基线，任务表现以及语言遵循、语义推理和鲁棒性得到改善，说明智能体代码能够连接 WAM 中的规划、预测与执行。

Recent world action models provide visual foresight and future prediction for robot manipulation, but lack explicit mechanisms for compositional skill reuse. Agentic robotics combines code-based planning and reasoning with reusable skills, but often lacks predictive grounding in physical dynamics. We introduce AW-0, an agentic world action model framework that integrates code-based planning with joint video and action prediction.

We jointly model code, future video, and robot actions as three coupled generative streams within a unified mixture-of-transformers architecture. Within this architecture a code expert generates parameterized skill routines and control logic while video and action experts generate future visual states and low-level motor commands.

Code serves two complementary roles: it structures multi-step prediction and control within the world model and represents skills as reusable programs for subsequent agentic execution. We further introduce an automated curation pipeline that labels robot and human video trajectories with aligned programs and consolidates recurring routines into reusable skill libraries.

Evaluations on RoboTwin 2.0 and physical bimanual manipulation tasks show improved task performance over VLA and WAM baselines, alongside gains in language following, semantic reasoning and robustness, demonstrating that agentic code enables connection between planning, prediction and execution within WAMs.