Papers
arxiv:2611.20011

ReactBench-AD: Do Driving VLAs and World-Action Models React to Imminent Hazards in Their Path?

Published on Nov 15
Authors:
,
,
,
,
,
,
,

Abstract

A new benchmark reveals that current Vision-Language-Action and World-Action autonomous driving models react weakly to objects in their path, though brief fine-tuning can substantially improve safety-critical braking with generalization to unseen and real scenes.

Vision-Language-Action models (VLAs) and World-Action Models (WAMs) have emerged in autonomous driving with the promise of strong generalization to long-tail scenarios. Although these models achieve state-of-the-art results on autonomous driving benchmarks, most existing benchmarks are dominated by nominal scenarios and therefore cannot test this promise. To test one such long-tail capability that is critical for safety, we introduce ReactBench-AD, a benchmark that measures how driving models react to objects that appear in the ego vehicle's path. Built on real NAVSIM and PhysicalAI-Autonomous-Vehicles scenes, ReactBench-AD composites a crossing pedestrian, a standing pedestrian, or a stationary car consistently across all camera views and history frames. Each edited scene thus forms an exact, pixel-level counterfactual pair with its original, which allows us to isolate the causal effect of the inserted object on the predicted trajectory. Evaluating four VLAs and two WAMs, we find that they react weakly, often barely at all. Finally, we test how easily one of the evaluated VLAs, ReCogDrive, can be taught to brake hard for imminent hazards: a short fine-tuning stage on edited scenes substantially improves its reactions, with the learned behavior generalizing to unseen objects and fully real scenes, at minimal cost to nominal driving. These results call into question the out-of-the-box long-tail capabilities of these models, but suggest that they can be a strong foundation for acquiring them with little additional training, highlighting the value of real or synthetic data that demonstrates the long-tail behaviors nominal datasets rarely contain. Code and data will be made publicly available.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2611.20011
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2611.20011 in a model README.md to link it from this page.

Datasets citing this paper 1

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2611.20011 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.