# Is VLA Reasoning Faithful? Probing Safety of Chain-of-Causation in Autonomous Driving Models

arXiv: https://arxiv.org/abs/2605.17268 · HTML: https://mlsanity.com/paper/2605.17268/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in VLA for autonomous driving, one of 13 directions in Vision-language-action models.
- Builds on 7 of its 13 references that are in the map.
- First posted on arXiv 17 May 2026.

## Placed in

- Vision-language-action models / [VLA for autonomous driving](https://mlsanity.com/vla/vla-for-autonomous-driving/)
- End-to-end autonomous driving / [Reasoning VLA and VLM driving policies](https://mlsanity.com/driving/reasoning-vla-and-vlm-driving-policies/)

## Builds on (most cited first, 7 of 7)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting](https://mlsanity.com/paper/2305.04388/) (2023)
- [Measuring Faithfulness in Chain-of-Thought Reasoning](https://mlsanity.com/paper/2307.13702/) (2023)
- [DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models](https://mlsanity.com/paper/2402.12289/) (2024)
- [Alpamayo-R1: Bridging Reasoning and Action Prediction for Generalizable Autonomous Driving in the Long Tail](https://mlsanity.com/paper/2511.00088/) (2025)
- [On a Formal Model of Safe and Scalable Self-driving Cars](https://mlsanity.com/paper/1708.06374/) (2017)

## Built on by (most cited first, 2 of 2)

- [Drive the Thoughts: Runtime Monitoring of VLA Reasoning-Trajectory Consistency](https://mlsanity.com/paper/2608.29583/) (2026)
- [When Reasoning Helps Action: Monitoring and Steering Chain-of-Thought in Vision-Language-Action Policies](https://mlsanity.com/paper/2610.00601/) (2026)

## Abstract (arXiv)

We present the first systematic study of faithfulness in Vision-Language-Action (VLA) driving models, analyzing 300 Alpamayo-R1-10B inferences across 100 diverse PhysicalAI-AV scenarios. Our main finding is that output natural-language rationales with trajectories may be significantly unfaithful: (i) overall reasoning fidelity is only 42.5%, with Chain-of-Causation matching scene reality less than half the time; (ii) 94 missed pedestrians in one-third of pedestrian-relevant scenes; (iii) 97.7% trajectory fragility under mild visual perturbations; and (iv) only 48.3% mean reasoning-action consistency, with 53.3% of inferences exhibiting low consistency, including 37.9% of stop-claimed cases where the model continues instead. We formalize faithfulness information-theoretically, define entity and action fidelity with verification criteria, and outline a four-component safety architecture aligned with these results.