# A2-MEAS框架发布：代码驱动纠错，BEHAVIOR基准Q分超冠军2.2倍

> 原文链接：https://robotics.hellobike.com/papers/2026-11-06-2611-09124-727d5469
> 频道：papers | 更新日期：2026-11-06 | 标签：auto, arxiv, hf-daily-papers
> 核心摘要：提出A2-MEAS具身多智能体框架，以代码为扩展接口实现高效纠错。在BEHAVIOR 2026获0.6411 Q-score，真机任务成功率57.92%显著优于pi0.5，训练吞吐提升4倍，将开源全栈系统。

# A2-MEAS框架发布：代码驱动纠错，BEHAVIOR基准Q分超冠军2.2倍

::: v-pre
> 本文由 AI 根据公开内容整理，可能有误，请以原文为准：[Toward the Era of Agentic Embodied Intelligence](https://arxiv.org/abs/2611.09124)（HF Daily Papers · arXiv 2611.09124）

## 核心内容

针对具身智能长程自主性与故障恢复难题，研究团队推出A2-MEAS框架及A2-WLA动作模型。该方案在BEHAVIOR 2026公开子集取得0.5755 Q-score，是2025年冠军成绩的2.21倍；在全量100项任务中Q-score达0.6411、成功率45.40%。RoboTwin 2.0平均成功率95.05%，12项真实家庭任务成功率57.92%，较pi0.5的26.67%提升逾一倍。

技术核心是将纠正语言、空间证据与执行历史编码为可学习修正码，通过MetaBrain提供监督；训练时由编码器注入策略权重，部署时冻结权重仅靠新代码适配行为。A2-WLA集成运动感知历史与潜在世界模型，在手冲咖啡等长程任务中将失败后完成率从14%提升至94%。训练基础设施采样率达427.1 samples/s，为pi0.5同硬件下的4.03倍，并将开源模型与脚本。

## 关键看点

- **基准性能**：BEHAVIOR 2026全量任务Q-score 0.6411、成功率45.40%，子集成绩达2025冠军2.21倍
- **真机验证**：5类家庭场景12项任务平均成功率57.92%，较pi0.5基线提升31.25个百分点
- **纠错机制**：历史条件适配器使手冲咖啡关键步骤失败后完成率从14%跃升至94%
- **训练效率**：采样吞吐427.1 samples/s，同等硬件下为pi0.5参考实现的4.03倍

## 工程与产业观察

该工作验证了“代码即接口”在具身智能中的工程价值：通过结构化修正码解耦策略学习与运行时适配，在不增加推理算力的前提下大幅提升长程任务鲁棒性。其开源承诺与4倍训练加速为社区提供了可复现的高效VLA训练范式，对解决真机数据稀缺与故障恢复具有直接参考意义。

## 英文摘要 (Abstract)

Foundation models increasingly guide robot actions, yet sustained autonomy requires efficient control and failure recovery. We introduce A2-MEAS, an embodied multi-agent framework built around code as a scaling interface. Learned correction codes combine corrective language, spatial evidence, execution history, and action proposals. MetaBrain provides training supervision and runtime guidance. A correction encoder and adapter absorb this knowledge into policy weights during training, while fresh codes adapt behavior with frozen weights at deployment. The action model, A2-WLA, adds motion-aware history and a latent world model to a vision-language-action policy. Surprisingly, this simple design with action pretraining and task specialization reaches 0.5755 Q-score on the 50-task BEHAVIOR 2026 public subset before online correction, 2.21x the 2025 winner's reported 0.2605 across different benchmark editions and training configurations. On all 100 BEHAVIOR 2026 public tasks, A2-MEAS achieves 0.6411 Q-score and 45.40% task success. On RoboTwin 2.0, A2-WLA achieves 93.98% average success, rising to 95.05% with the complete system. Across 12 real-robot tasks in five household settings, A2-WLA achieves 57.92% average success versus 26.67% for pi0.5. In long-horizon pour-over coffee preparation, a history-conditioned adapter raises post-failure completion at two filter-handling steps from 14% to 94% and from 8% to 82%, compared with A2-WLA retries. Our training infrastructure delivers 427.1 samples per second, 4.03x the throughput of a pi0.5 reference implementation on matched hardware. We will release the system, models, training scripts, and infrastructure to support efficient embodied learning.

Hugging Face Daily Papers 热度：45 upvotes
作者：Chao Liang, Ke Chen, Fengxiaoxiao Li, Shibo Huang, Yufeng Sun, Zhaokai Yin, Jianhuan Lai, Haozhe Feng, Chenghuan Jia, Zhipeng Zhang
:::

## 原始参考来源 (Sources)

- [HF Daily Papers · arXiv 2611.09124：Toward the Era of Agentic Embodied Intelligence](https://arxiv.org/abs/2611.09124)