---
id: 20260812-T0-04
title: "CMU-Drive与V2V-VLA：多智能体协同驾驶基准与车对车视觉语言动作模型发布"
title_en: "CMU-Drive and V2V-VLA: Cooperative Driving Benchmark and Vehicle-to-Vehicle VLA Models"
url: https://ai.daily.yangsir.net/daily/20260812-T0-04
issue_date: 2026-08-12
publish_date: 2026-08-11T04:00:00.000Z
category: research
source_name: "arXiv cs.AI"
source_url: https://arxiv.org/abs/2608.07621
---

# CMU-Drive与V2V-VLA：多智能体协同驾驶基准与车对车视觉语言动作模型发布

arXiv新论文发布CMU-Drive基准和V2V-VLA模型，推动多智能体协同自动驾驶研究。CMU-Drive提供带推理标注的协同驾驶基准测试，V2V-VLA是车对车的视觉语言动作模型，支持多车辆间的感知融合与动作协调。现有VLA模型多为单智能体设计，该研究填补了协同驾驶场景的空白。

## English Version

**CMU-Drive and V2V-VLA: Cooperative Driving Benchmark and Vehicle-to-Vehicle VLA Models**

New paper presents CMU-Drive, a cooperative driving benchmark with reasoning annotations, and V2V-VLA, a vehicle-to-vehicle vision-language-action model enabling multi-vehicle perception fusion and coordinated action. Addresses the gap in cooperative driving for existing single-agent VLA models.

---

**来源**：[arXiv cs.AI](https://arxiv.org/abs/2608.07621)

**详情页**：https://ai.daily.yangsir.net/daily/20260812-T0-04

---

*智语观潮 · Daily — https://ai.daily.yangsir.net/llms.txt*