# FLEX-WAM：用于长时域想象与规划的灵活块因果世界-动作模型

> 原文链接：https://robotics.hellobike.com/papers/2026-10-04-2610-05483
> 频道：papers | 更新日期：2026-10-04 | 标签：arxiv, cs.RO
> 核心摘要：FLEX-WAM用块因果可缓存世界-动作模型解决长时域高效稳定想象与规划，并在仿真、真实数据和机器人上验证。

# FLEX-WAM：用于长时域想象与规划的灵活块因果世界-动作模型

::: v-pre
> 原文链接：[FLEX-WAM: Flexible Block-Causal World-Action Models for Long-Horizon Imagination and Planning](https://arxiv.org/abs/2610.05483)（arXiv 2610.05483 · 发布日期：2026-10-04）

**FLEX-WAM: Flexible Block-Causal World-Action Models for Long-Horizon Imagination and Planning**

FLEX-WAM用块因果可缓存世界-动作模型解决长时域高效稳定想象与规划，并在仿真、真实数据和机器人上验证。

## 核心要点

- 现有联合视频-动作模型计算开销大、固定时域，难适配流式推断和稳定长时域开环滚动。
- 模型支持可变长度上下文、非因果预测时域，以及逐帧或逐块无限自回归生成。
- 采用块因果KV缓存架构，结合轴向注意力和分块diffusion forcing提升部署效率。
- 在仿真和真实数据上提升多步预测质量与延迟，并在MCTS中完成长时域想象规划任务。

**验证范围与局限**：验证范围包括仿真和真实世界数据集、PushT与OGBench Puzzle-4x4想象规划任务，以及基于OpenArm的双臂机器人。

## 英文摘要 (Abstract)

World--action models (WAMs) promise a unified model that predicts action-conditioned futures, generates feasible actions, and supports planning in imagination. However, existing joint video--action models often use computationally heavy, fixed-horizon backbones ill-suited to streaming inference and stable long-horizon open-loop rollouts. We introduce FLEX-WAM, a Flexible and Efficient Block-Causal World--Action Model for unified simulation and policy inference. FLEX-WAM supports variable-length contexts and non-causal prediction horizons, as well as infinite autoregressive generation frame by frame or block by block. Its block-causal, KV-cacheable architecture combines axial attention and blockwise diffusion forcing to enable efficient real-time rollout and deployment-time latency--throughput tradeoffs without retraining. Joint training can nevertheless produce plausible futures that weakly respond to commanded actions. We address this failure mode by balancing state and action flow-matching gradient contributions across the state--action diffusion-noise grid and regulating world-model sampling using Forward-Dynamics (FD) elasticity, an efficient training-time proxy for action responsiveness. Across simulated and real-world datasets, FLEX-WAM achieves superior multi-step prediction quality and latency while producing stable joint state--action rollouts for thousands of steps. As a joint action proposer and simulator within MCTS, it solves long-horizon PushT and all five OGBench Puzzle-4x4 tasks entirely in imagination. On a bimanual OpenArm-based robot, a single checkpoint jointly serves as a play policy and expected-outcome predictor, enabling real-time identification and collection of model--reality mismatches for future self-improvement.

作者：Rooholla Khorrambakht, Joseph Amigo, Félix Lebel, Leon Seetoo, Jean Ponce, Zhenzhen Li, Ludovic Righetti
:::

## 原始参考来源 (Sources)

- [arXiv 2610.05483：FLEX-WAM: Flexible Block-Causal World-Action Models for Long-Horizon Imagination and Planning](https://arxiv.org/abs/2610.05483)