Reasoning as a Double-Edged Sword: Architecture and Cross-Stage Robustness in Vision-Language-Action Models

• URL: http://arxiv.org/abs/2607.17786v1
• Date: Mon, 20 Jul 2026 10:20:32 GMT
• Title: Reasoning as a Double-Edged Sword: Architecture and Cross-Stage Robustness in Vision-Language-Action Models
• Abstract summary: Policy that reasons before acting should absorb a perturbed input better than one that maps observations directly to actions.<n>We test this premise head-on across three models that span the reasoning spectrum.<n>We find that the latent-iterative model is by far the least robust.
• Score: 27.2709460237741
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Does adding a reasoning step make a Vision-Language-Action (VLA) model more robust to perturbation? Intuitively, a policy that reasons before acting should absorb a perturbed input better than one that maps observations directly to actions. We test this premise head-on across three models that span the reasoning spectrum (no reasoning, a text chain-of-thought, and a latent iterative loop), perturbing each at the vision, reasoning, and action stages on LIBERO and SimplerEnv. Two questions organize the study: does the reasoning design shift robustness, and can the reasoning be read back at runtime as a safety signal? We find that the latent-iterative model is by far the least robust: under both stochastic noise and white-box perturbation its task success collapses, while the other two hold. This fragility is structural rather than cumulative: varying the reasoning depth at inference barely moves it. Reasoning outputs can in principle be monitored, but the monitors fail under fair tests. A plan--action consistency probe that looks near-perfect under naive evaluation falls to chance under adaptive attack. Under matched-FPR calibration, fusing it with an action-anomaly probe never lifts defended success above undefended. Scoped to these output-level behavioral probes under white-box vision-stage attack, this ceiling is a precondition that any viable defense must first satisfy.

Related papers

• LookAgain: Closed-Loop GUI Grounding with Visually Grounded Reflection [42.672264792698904]
  Recent graphical user interface (GUI) grounders have significantly advanced single-shot accuracy on standard benchmarks.<n>But their performance degrades sharply on small targets, densely packed controls and out-of-distribution interfaces.<n>We propose LookAgain, a closed-loop GUI grounder driven by post-prediction visual reflection.
  arXiv  Detail & Related papers  (2026-08-10T15:23:52Z)
• Bridging Physical Reasoning and Task Generalization via Visual Action Outcome Reasoning Alignment [67.2775785848366]
  Two key failure modes are prominent: hallucinated chain-of-thought (CoT) reasoning that contradicts physical reality, and misalignment between the model's reasoning and actions.<n>We present VAORA, a novel reward design that directly addresses both issues.<n>VAORA introduces two complementary rewards: Visual Alignment Reward, which anchors VLM reasoning to the visual context independent of the agent action itself, and Visual-Action Alignment Reward, which grounds reasoning in the visual outcome induced by the model's action.
  arXiv  Detail & Related papers  (2026-07-07T17:27:59Z)
• When the Chain of Thought Knows Better: Failure Modes in Multi-Turn Reasoning Models [7.185483586381928]
  Failures in multi-turn reasoning models are largely invisible to terminal-score evaluation.<n>A model can lock onto an unsafe stance early in a long dialogue, yet its final-turn refusal rate may appear indistinguishable from a robustly aligned baseline.<n>We propose a trace-level diagnostic - the CoT-Output 2x2 safety matrix.
  arXiv  Detail & Related papers  (2026-06-09T11:50:28Z)
• Behavior Cue Reasoning: Monitorable Reasoning Improves Efficiency and Safety through Oversight [8.531991753482838]
  Reasoning in Large Language Models (LLMs) poses a challenge for oversight.<n>We introduce Behavior Cue Reasoning for making LLM reasoning more controllable and monitorable.
  arXiv  Detail & Related papers  (2026-05-07T23:05:50Z)
• Ulterior Motives: Detecting Misaligned Reasoning in Continuous Thought Models [0.0]
  Chain-of-Thought (CoT) reasoning has emerged as a key technique for eliciting complex reasoning in Large Language Models (LLMs)<n>We introduce MoralChain, a benchmark of 12,000 social scenarios with parallel moral/immoral reasoning paths.<n>We show that continuous thought models can exhibit misaligned latent reasoning while producing aligned outputs.
  arXiv  Detail & Related papers  (2026-04-25T22:43:15Z)
• How Does Prefix Matter in Reasoning Model Tuning? [57.69882799751655]
  We fine-tune three R1 series models across three core model capabilities: reasoning (mathematics), coding, safety, and factuality.<n>Results show that prefix-conditioned SFT improves both safety and reasoning performance, yielding up to +6% higher Safe@1 accuracy.
  arXiv  Detail & Related papers  (2026-01-04T18:04:23Z)
• Counterfactual VLA: Self-Reflective Vision-Language-Action Model with Adaptive Reasoning [71.19675094463834]
  This work introduces Counterfactual VLA, a self-reflective VLA framework that enables the model to reason about and revise its planned actions before execution.<n>CF-VLA first generates time-segmented meta-actions that summarize driving intent, and then performs counterfactual reasoning conditioned on both the meta-actions and the visual context.<n> Experiments on large-scale driving datasets show that CF-VLA improves trajectory accuracy by up to 17.6%, enhances safety metrics by 20.5%, and exhibits adaptive thinking.
  arXiv  Detail & Related papers  (2025-12-30T19:04:17Z)
• Hallucination Detection via Internal States and Structured Reasoning Consistency in Large Language Models [7.18947815679122]
  Internal State Probing and Chain-of-Thought Verification are used to detect hallucinations in large language models.<n>We develop a unified framework that bridges the gap between the two methods.<n>Our framework consistently and significantly outperforms strong baselines.
  arXiv  Detail & Related papers  (2025-10-13T15:31:21Z)
• VOGUE: Guiding Exploration with Visual Uncertainty Improves Multimodal Reasoning [62.09195763860549]
  Reinforcement learning with verifiable rewards (RLVR) improves reasoning in large language models (LLMs) but struggles with exploration.<n>We introduce $textbfVOGUE (Visual Uncertainty Guided Exploration)$, a novel method that shifts exploration from the output (text) to the input (visual) space.<n>Our work shows that grounding exploration in the inherent uncertainty of visual inputs is an effective strategy for improving multimodal reasoning.
  arXiv  Detail & Related papers  (2025-10-01T20:32:08Z)
• Landscape of Thoughts: Visualizing the Reasoning Process of Large Language Models [58.64449765678416]
  We introduce landscape of thoughts (LoT) to inspect the reasoning trajectories with certain reasoning methods on any multi-choice dataset.<n>LoT distinguishes between strong and weak models, correct and incorrect answers, as well as different reasoning tasks.<n>We showcase this advantage by adapting LoT to a lightweight verifier that evaluates the correctness of trajectories.
  arXiv  Detail & Related papers  (2025-03-28T06:09:51Z)
• Unveiling the Magic of Code Reasoning through Hypothesis Decomposition and Amendment [54.62926010621013]
  We introduce a novel task, code reasoning, to provide a new perspective for the reasoning abilities of large language models.<n>We summarize three meta-benchmarks based on established forms of logical reasoning, and instantiate these into eight specific benchmark tasks.<n>We present a new pathway exploration pipeline inspired by human intricate problem-solving methods.
  arXiv  Detail & Related papers  (2025-02-17T10:39:58Z)

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.