Unmasking the Illusion of Embodied Reasoning in Vision-Language-Action Models

• URL: http://arxiv.org/abs/2604.18000v1
• Date: Mon, 20 Apr 2026 09:25:30 GMT
• Title: Unmasking the Illusion of Embodied Reasoning in Vision-Language-Action Models
• Abstract summary: Recent Vision-Language-Action (VLA) models report impressive success rates on standard robotic benchmarks.<n>Recent evidence suggests a systematic misalignment between standard benchmark success and true embodied reasoning.<n>We introduce BeTTER, a diagnostic Benchmark for Testing True Embodied Reasoning in robotic policies.
• Score: 28.981226513192535
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent Vision-Language-Action (VLA) models report impressive success rates on standard robotic benchmarks, fueling optimism about general-purpose physical intelligence. However, recent evidence suggests a systematic misalignment between standard benchmark success and true embodied reasoning, raising the question of whether these high scores reflect genuine cognitive capability. To address this gap, we introduce BeTTER, a diagnostic Benchmark for Testing True Embodied Reasoning in robotic policies. BeTTER applies targeted causal interventions (e.g., spatial layout shifts, temporal extrapolation) while enforcing kinematic isolation to explicitly decouple high-level reasoning failures from low-level execution limits. Through systematic evaluation, we reveal that state-of-the-art VLAs catastrophically fail in dynamic scenarios, exhibiting severe lexical-kinematic shortcuts, behavioral inertia, and semantic feature collapse. Crucially, our mechanistic analysis traces these symptoms to fundamental architectural bottlenecks - such as capacity compression and myopic downsampling - which systematically degrade the model's foundational semantic representation. We demonstrate that highly static evaluation protocols effectively mask this degradation by allowing optimization to overfit to sensorimotor priors. Supported by real-world robotic validation, our findings confirm that this representational breakdown is not a simulation artifact, highlighting the critical need for future VLA paradigms to resolve the structural tension between high-frequency control and high-level reasoning.

Related papers

• CofactVLA: Deconfounding Vision-Language-Action Models via Counterfactual Intervention [48.20065816234311]
  Vision-Language-Action (VLA) models have driven significant progress in robotic manipulation, yet they struggle with the vision-override phenomenon.<n>We propose CofactVLA, a novel causal intervention framework.<n>We show that CofactVLA establishes a new state-of-the-art across diverse simulation benchmarks.
  arXiv  Detail & Related papers  (2026-08-05T02:58:41Z)
• ThinkingVLA: Interleaved Vision and Language Reasoning for Robotic Manipulation [71.69632267962993]
  We argue that manipulation planning naturally decomposes into prediction, anticipating the next visual state, and inverse dynamics.<n>We propose textbfThinkingVLA, a generative model that realizes this decomposition within a unified Mixture-of-Transformers architecture.<n>Experiments on simulation and real-world benchmarks demonstrate that ThinkingVLA consistently outperforms state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-06-16T13:45:17Z)
• FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection [39.012577080756735]
  We propose FakeVLM-R1, aiming to endow the model with human-like critical thinking capabilities.<n>FakeVLM-R1 achieves high-precision, logically interpretable detection.<n>It also resolves the over-rejection bias of existing methods against real images.
  arXiv  Detail & Related papers  (2026-05-28T15:13:31Z)
• Provably Secure Agent Guardrail [89.79561918065122]
  Existing defense architectures rely on empirical semantic guardrails and probabilistic large model adjudicators.<n>This paper proposes a new security paradigm for agents based on the fundamental limitations of logical reasoning.
  arXiv  Detail & Related papers  (2026-05-28T02:12:41Z)
• Beyond Binary Success: A Diagnostic Meta-Evaluation Framework for Fine-Grained Manipulation [98.79811866787263]
  We introduce MetaFine, a diagnostic meta-evaluation framework that disentangles manipulation competency along three axes.<n>We identify the visual encoder's ability to preserve local spatial structure as a key bottleneck for fine-grained precision.<n>By shifting evaluation from ranking to diagnosis, MetaFine turns benchmarking into an actionable compass for repairing the layered capacities underlying genuine physical dexterity.
  arXiv  Detail & Related papers  (2026-05-19T15:25:13Z)
• From Noise to Intent: Anchoring Generative VLA Policies with Residual Bridges [39.128014667094014]
  ResVLA is an architecture that shifts the paradigm to "Refinement-from-Noise-Intent"<n>It focuses on refining local dynamics via a residual diffusion bridge.<n>It demonstrates strong performance in real-world robot experiments.
  arXiv  Detail & Related papers  (2026-04-23T07:59:26Z)
• Anatomy of a Lie: A Multi-Stage Diagnostic Framework for Tracing Hallucinations in Vision-Language Models [62.932580559941414]
  Vision-Language Models (VLMs) frequently "hallucinate" - generate plausible yet factually incorrect statements.<n>We propose a new paradigm for diagnosing hallucinations, recasting them from static output errors into dynamic pathologies of a model's computational cognition.
  arXiv  Detail & Related papers  (2026-03-16T17:20:38Z)
• Act, Think or Abstain: Complexity-Aware Adaptive Inference for Vision-Language-Action Models [7.802379200026965]
  We propose an adaptive framework that dynamically routes VLA execution based on the complexity of the perceived state.<n>Our approach transforms the VLA's vision-language backbone into an active detection tool by projecting latent embeddings into an ensemble of parametric and non-parametric estimators.
  arXiv  Detail & Related papers  (2026-03-05T13:14:41Z)
• Advancing Analytic Class-Incremental Learning through Vision-Language Calibration [6.871141687303144]
  Class-incremental learning (CIL) with pre-trained models (PTMs) faces a critical trade-off between efficient adaptation and long-term stability.<n>We propose textbfVILA, a novel dual-branch framework that advances analytic CIL via a two-level vision-language calibration strategy.<n>Our framework harmonizes high-fidelity prediction with the simplicity of analytic learning.
  arXiv  Detail & Related papers  (2026-02-14T08:32:51Z)
• Understanding Degradation with Vision Language Model [56.09241449206817]
  Understanding visual degradations is a critical yet challenging problem in computer vision.<n>We introduce DU-VLM, a multimodal chain-of-thought model trained with supervised fine-tuning and reinforcement learning.<n>We also introduce textbfDU-110k, a large-scale dataset comprising 110,000 clean-degraded pairs with grounded physical annotations.
  arXiv  Detail & Related papers  (2026-02-04T13:51:15Z)
• Unified Embodied VLM Reasoning with Robotic Action via Autoregressive Discretized Pre-training [16.28589738595606]
  General-purpose robotic systems must achieve broad generalization and high-precision action execution.<n>We introduce Embodied Reasoning Intelligence Quotient (ERIQ), a large-scale embodied reasoning benchmark in robotic manipulation.<n>We propose FACT, a flow-matching-based action tokenizer that converts continuous control into discrete sequences.
  arXiv  Detail & Related papers  (2025-12-30T10:18:42Z)
• Robust-R1: Degradation-Aware Reasoning for Robust Visual Understanding [54.05243949024302]
  Existing robust MLLMs rely on implicit training/adaptation that focuses solely on visual encoder generalization.<n>We propose Robust-R1, a novel framework that explicitly models visual degradations through structured reasoning chains.<n>Our approach integrates: (i) supervised fine-tuning for degradation-aware reasoning foundations, (ii) reward-driven alignment for accurately perceiving degradation parameters, and (iii) dynamic reasoning depth scaling adapted to degradation intensity.
  arXiv  Detail & Related papers  (2025-12-19T12:56:17Z)
• LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models [49.92148175114169]
  We perform a systematic vulnerability analysis by introducing controlled perturbations across seven dimensions.<n>Models exhibit extreme sensitivity to perturbation factors, including camera viewpoints and robot initial states.<n>Surprisingly, models are largely insensitive to language variations, with further experiments revealing that models tend to ignore language instructions completely.
  arXiv  Detail & Related papers  (2025-10-15T14:51:36Z)
• Sycophancy Mitigation Through Reinforcement Learning with Uncertainty-Aware Adaptive Reasoning Trajectories [58.988535279557546]
  We introduce textbf sycophancy Mitigation through Adaptive Reasoning Trajectories.<n>We show that SMART significantly reduces sycophantic behavior while preserving strong performance on out-of-distribution inputs.
  arXiv  Detail & Related papers  (2025-09-20T17:09:14Z)
• Sycophancy in Vision-Language Models: A Systematic Analysis and an Inference-Time Mitigation Framework [18.54098084470481]
  We analyze sycophancy across vision-language benchmarks and propose an inference-time mitigation framework.<n>Our framework effectively mitigates sycophancy across all evaluated models, while maintaining performance on neutral prompts.
  arXiv  Detail & Related papers  (2024-08-21T01:03:21Z)

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.