论文/arXiv 2610.17540·15 天前

TacitVLA：无推理延迟的推理型 VLA 模型

TacitVLA让动作专家不关注当前生成推理，在操控与自动驾驶等四个基准上验证低延迟推理VLA。

AI 整理

• 本体 SDK 与控制
• 具身模型
• 端侧部署

原文链接：TacitVLA: Reasoning Vision-Language-Action Models Without Reasoning Latency（arXiv 2610.17540 · 发布日期：2026-10-13）

TacitVLA: Reasoning Vision-Language-Action Models Without Reasoning Latency

TacitVLA让动作专家不关注当前生成推理，在操控与自动驾驶等四个基准上验证低延迟推理VLA。

核心要点

• 先生成文本推理可提升VLA，但动作需等待自回归解码，带来延迟。
• TacitVLA利用推理监督改进骨干表示，动作专家不关注当前调用生成的推理。
• 在长时程任务中，作为情节记忆的推理条目可在动作执行期间生成。
• 四个基准上匹配显式推理性能，延迟最高低3.4倍；同等延迟下成功率最高+17.1%。

验证范围与局限：验证限于RoboMME、RMBench、LIBERO和PhysicalAI-AV四个基准，覆盖操控与自动驾驶、记忆与非记忆任务。

英文摘要 (Abstract)

Textual reasoning before acting has improved vision-language-action (VLA) models, but at the cost of latency: every action conditioned on the reasoning text must wait for autoregressive decoding. We show that actions do not need to wait for or condition on the generated reasoning to benefit from it, because the reasoning supervision already improves the backbone representation. We introduce TacitVLA, a reasoning VLA whose action expert never attends to the reasoning it generates for the current call. On long-horizon tasks where the reasoning text also serves as episodic memory, it can generate each entry during action execution rather than before acting. We evaluate it in a controlled study on four benchmarks spanning manipulation and autonomous driving, memory and non-memory tasks: RoboMME, RMBench, LIBERO, and PhysicalAI-AV. On all four, TacitVLA matches the performance of its explicit-reasoning counterpart at up to 3.4x lower latency, and matches the latency of the same architecture trained without reasoning at up to +17.1% success. In absolute terms, it surpasses the best previously published results on the RoboMME Counting suite (82.7% vs. 66.8%) and RMBench (77.5% vs. 56.5%), and reaches 72.9% on LIBERO-Plus and a 52.5% scene score on the public split of the PhysicalAI-AV closed-loop driving challenge. Project page: https://tacitvla.github.io.

作者：Jack Lu, Yurong You, Boyi Li, Yulong Cao, Thomas Tian, Chaowei Xiao, Xiangyu Chen, Wenjie Luo, Boris Ivanovic, Marco Pavone

来源

本页事实对应的公开页面，以原文为准。

1. arXiv 2610.17540：TacitVLA: Reasoning Vision-Language-Action Models Without Reasoning Latency访问 2026-10-21