Drive the Thoughts: Runtime Monitoring of VLA Reasoning-Trajectory Consistency

• URL: http://arxiv.org/abs/2608.29583v1
• Date: Sun, 30 Aug 2026 06:03:34 GMT
• Title: Drive the Thoughts: Runtime Monitoring of VLA Reasoning-Trajectory Consistency
• Abstract summary: Chain-of-Thought (CoT) is a rich specification to cross-check model outputs.<n>This paper assesses whether CoTs from a recent open driving VLA can support such monitoring.<n>We propose integrating a CoT-trajectory consistency check into a runtime monitor.
• Score: 7.931305046286546
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Autonomous vehicles (AVs) operate in complex environments where failures are consequential. Sophisticated machine learning models for perception and planning are key to overcoming at least part of that complexity, but their black-box nature complicates validation and verification (V&V). The recent integration of Vision-Language-Action (VLA) models into AVs introduces a unique opportunity: besides generating trajectories, these models produce an explicit Chain-of-Thought (CoT) explaining their underlying rationale. This CoT provides a rich specification to cross-check model outputs and detect inconsistencies that may expose unsafe or unintended behavior. This paper assesses whether CoTs from a recent open driving VLA can support such monitoring. We curate DriveAlignBench, a specialized dataset from NVIDIA's Alpamayo 1.5 VLA for AVs containing 150 CoT-trajectory pairs, which we manually annotate for reliability, trajectory consistency, and safety. Our analysis reveals that 33.3% of CoTs are unreliable. Among reliable CoTs, the generated trajectory is consistent with the CoT in 74% of cases. Leveraging this potential, we propose integrating a CoT-trajectory consistency check into a runtime monitor. The check is nontrivial: CoTs express open-vocabulary, scene-relative driving commitments, while trajectories are low-level ego-motion sequences whose semantics depend on road geometry and motion context. To bridge this gap, we develop a family of automated consistency monitors. Our best monitor, lane-relative F-LLM with GPT-5.5, achieves F1 = 0.75, improving over the strongest raw-waypoint LLM baseline by +0.13 absolute F1 and over a rule-based monitor by +0.38. We release DriveAlignBench, the monitor implementations, and annotation tools at https://github.com/776styjsu/drive-the-thoughts.

Related papers

• GenTrack3: Hybrid Stochastic-Deterministic Online Multi-Object Tracking with Cluster-Aware Association [3.259045978275386]
  Multi-object tracking (MOT) involves maintaining consistent target identities as objects dynamically enter and leave a scene.<n>This paper presents an online framework that integrates deterministic and inference principles to achieve robust tracking under uncertainty.
  arXiv  Detail & Related papers  (2026-08-10T13:16:17Z)
• CIAware-Bench: Benchmarking Control Intervention Awareness Across Frontier LLMs [100.38986535324284]
  We introduce textbfCIAware-Bench, a benchmark for measuring textbfcontrol textbfintervention (CI) awareness across frontier models.<n>CIAware-Bench tests whether models can distinguish their own trajectories from those modified by a control intervention.
  arXiv  Detail & Related papers  (2026-06-09T16:24:16Z)
• How VLAs Fail Differently: Black-Box Action Monitoring Reveals Architecture-Specific Failure Signatures [0.0]
  We find that VLA architectures fail in fundamentally different, predictable ways at the motor-command level.<n>We quantify consequence of the well-known discrete/continuous VLA distinction: the two families produce qualitatively different failure monitor works.
  arXiv  Detail & Related papers  (2026-05-27T16:44:55Z)
• OneDrive: Unified Multi-Paradigm Driving with Vision-Language-Action Models [69.2503510410147]
  We present a unified autonomous driving framework built upon a pretrained VLM.<n>We demonstrate that pretrained VLM attention exhibits strong transferability beyond pure language modeling.<n>Experiments on end-to-end autonomous driving benchmarks demonstrate state-of-the-art performance.
  arXiv  Detail & Related papers  (2026-04-20T07:50:00Z)
• Bench2Drive-VL: Benchmarks for Closed-Loop Autonomous Driving with Vision-Language Models [50.22099309218635]
  In autonomous driving, closed-loop evaluation has become widely recognized as a more reliable validation method than open-loop evaluation.<n>We present Bench2Drive-VL, an extension of Bench2Drive that brings closed-loop evaluation to VLM-based driving.
  arXiv  Detail & Related papers  (2026-04-01T11:38:46Z)
• COVTrack++: Learning Open-Vocabulary Multi-Object Tracking from Continuous Videos via a Synergistic Paradigm [59.26203051651017]
  C-TAO is the first continuously annotated training set for Open-Vocabulary Multi-Object Tracking (OVMOT)<n>For the framework bottleneck, we propose COVTrack++, a synergistic framework that achieves a bidirectional reciprocal mechanism between detection and association through three modules.<n>Experiments on TAO demonstrate state-of-the-art performance, with novel TETA reaching 35.4% and 30.5% on validation and test sets, improving novel AssocA by 4.8% and novel LocA by 5.8% over previous methods.
  arXiv  Detail & Related papers  (2026-03-25T07:20:27Z)
• Measuring Chain-of-Thought Monitorability Through Faithfulness and Verbosity [3.117948413097524]
  Chain-of-thought (CoT) outputs let us read a model's step-by-step reasoning.<n>We evaluate instruction-tuned and reasoning models on BBH, GPQA, and MMLU.
  arXiv  Detail & Related papers  (2025-10-31T11:14:39Z)
• A Pragmatic Way to Measure Chain-of-Thought Monitorability [10.811252340660907]
  Chain-of-Thought (CoT) monitoring offers a unique opportunity for AI safety.<n>To help preserve monitorability, we propose a pragmatic way to measure two components of it: legibility and coverage.<n>We implement these metrics with an autorater prompt that enables any capable LLM to compute the legibility and coverage of existing CoTs.
  arXiv  Detail & Related papers  (2025-10-28T00:44:25Z)
• Tracking the Unstable: Appearance-Guided Motion Modeling for Robust Multi-Object Tracking in UAV-Captured Videos [58.156141601478794]
  Multi-object tracking (UAVT) aims to track multiple objects while maintaining consistent identities across frames of a given video.<n>Existing methods typically model motion cues and appearance separately, overlooking their interplay and resulting in suboptimal tracking performance.<n>We propose AMOT, which exploits appearance and motion cues through two key components: an Appearance-Motion Consistency (AMC) matrix and a Motion-aware Track Continuation (MTC) module.
  arXiv  Detail & Related papers  (2025-08-03T12:06:47Z)
• Mitigating Deceptive Alignment via Self-Monitoring [15.365589693661823]
  We develop a framework that embeds a Self-Monitor inside the chain-of-thought process itself, named CoT Monitor+.<n>During generation, the model produces (i) ordinary reasoning steps and (ii) an internal self-evaluation signal trained to flag and suppress misaligned strategies.<n>The signal is used as an auxiliary reward in reinforcement learning, creating a feedback loop that rewards honest reasoning and discourages hidden goals.
  arXiv  Detail & Related papers  (2025-05-24T17:41:47Z)
• BEVTrack: A Simple and Strong Baseline for 3D Single Object Tracking in Bird's-Eye View [54.48052449493636]
  3D Single Object Tracking (SOT) is a fundamental task in computer vision and plays a critical role in applications like autonomous driving.<n>We propose BEVTrack, a simple yet effective motion-based tracking method.<n>We show that BEVTrack achieves state-of-the-art results while operating at 200 FPS, enabling real-time applicability.
  arXiv  Detail & Related papers  (2023-09-05T12:42:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.