DualVLA: Building a Generalizable Embodied Agent via Partial Decoupling of Reasoning and Action

• URL: http://arxiv.org/abs/2511.22134v1
• Date: Thu, 27 Nov 2025 06:03:53 GMT
• Title: DualVLA: Building a Generalizable Embodied Agent via Partial Decoupling of Reasoning and Action
• Abstract summary: We propose DualVLA, which enhances action performance through carefully designed post-training while still preserving reasoning capability.<n>Experiments show that DualVLA achieves an average success rate of 61.0 in SimplerEnv and an average score of 65.4 across eight competitive multimodal benchmarks.
• Score: 62.70893433854428
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: To build a generalizable Vision-Language-Action (VLA) model with strong reasoning ability, a common strategy is to first train a specialist VLA on robot demonstrations to acquire reliable manipulation skills, and then incorporate mixed annotated robot data together with multimodal data to restore broader reasoning capabilities. However, we observe that the resulting reasoning VLA often suffers from degraded action performance compared to the specialist model before fine-tuning, a phenomenon we refer to as action degeneration. To address this issue, we propose DualVLA, which enhances action performance through carefully designed post-training while still preserving reasoning capability. We first introduce a dual-layer data pruning method that removes redundant embodied reasoning, preventing it from adversely influencing action learning. To further strengthen action generation, we design a dual-teacher adaptive distillation strategy that assigns different supervision signals to different data domains while maintaining reasoning ability. To fill the evaluation gap for generalist VLAs, we also propose VLA Score, which decouples VLA capability into reasoning, intention, action, and alignment dimensions for a more fine-grained assessment. Experiments show that DualVLA achieves an average success rate of 61.0 in SimplerEnv and an average score of 65.4 across eight competitive multimodal benchmarks, demonstrating a stronger balance between precise action execution and multimodal understanding. Project Website: https://costaliya.github.io/DualVLA/.

Related papers

• Revisiting Embodied Chain-of-Thought for Generalizable Robot Manipulation [24.465551417061494]
  Embodied chain-of-thought (CoT) aims to bridge linguistic reasoning and robotic control.<n>We construct the largest embodied CoT corpus to date, comprising 978,743 trajectories, 226.3M samples, and 2592.5 hours of robot data.
  arXiv  Detail & Related papers  (2026-06-02T15:37:59Z)
• UAM: A Dual-Stream Perspective on Forgetting in VLA Training [20.50709311546184]
  Vision--language--action (VLA) models are typically built by fine-tuning a pretrained vision--language model (VLM) on action data.<n>We show that this standard recipe systematically erodes the VLM's multimodal competence.<n>Inspired by the two-stream organization of biological vision, we trace this degradation to a structural bottleneck.
  arXiv  Detail & Related papers  (2026-05-15T08:45:37Z)
• SpanVLA: Efficient Action Bridging and Learning from Negative-Recovery Samples for Vision-Language-Action Model [16.077387927185917]
  Vision-Language-Action (VLA) models offer a promising autonomous driving paradigm for leveraging world knowledge and reasoning capabilities.<n>Existing VLA models often struggle with the high latency in action generation using an autoregressive generation framework.<n>We propose SpanVLA, a novel end-to-end autonomous driving framework, integrating an autoregressive reasoning and a flow-matching action expert.
  arXiv  Detail & Related papers  (2026-04-21T17:34:19Z)
• ReFineVLA: Multimodal Reasoning-Aware Generalist Robotic Policies via Teacher-Guided Fine-Tuning [10.039310538887833]
  Vision-Language-Action (VLA) models have gained much attention from the research community.<n>Despite their advancements, VLA models often overlook explicit reasoning and learn the functional input-action mappings.<n>We propose ReFineVLA, a multimodal reasoning-aware framework that fine-tunes VLA models with teacher-guided reasons.
  arXiv  Detail & Related papers  (2026-04-20T04:46:20Z)
• Reshaping Action Error Distributions for Reliable Vision-Language-Action Models [69.38615670891038]
  In robotic manipulation, vision-language-action (VLA) models have emerged as a promising paradigm for learning generalizable and scalable robot policies.<n>We focus on continuous-action VLA models and move beyond conventional MSE-based regression by reshaping action error distributions during training.<n>We evaluate our approaches across standard, few-shot, and noisy settings on multiple representative VLA architectures.
  arXiv  Detail & Related papers  (2026-02-04T05:37:09Z)
• Latent Reasoning VLA: Latent Thinking and Prediction for Vision-Language-Action Models [69.58413440457828]
  Vision-Language-Action (VLA) models benefit from chain-of-thought (CoT) reasoning, but existing approaches incur high inference overhead.<n>We propose Latent Reasoning VLA (textbfLaRA-VLA), a unified VLA framework that internalizes multi-modal CoT reasoning into continuous latent representations for embodied action.
  arXiv  Detail & Related papers  (2026-02-01T11:34:37Z)
• Steering Vision-Language-Action Models as Anti-Exploration: A Test-Time Scaling Approach [78.4812458793128]
  We propose textbfTACO, a test-time-scaling framework that applies a lightweight pseudo-count estimator as a high-fidelity verifier of action chunks.<n>Our method resembles the classical anti-exploration principle in offline reinforcement learning (RL), and being gradient-free, it incurs significant computational benefits.
  arXiv  Detail & Related papers  (2025-12-02T14:42:54Z)
• Dual-Stream Diffusion for World-Model Augmented Vision-Language-Action Model [62.889356203346985]
  We propose DUal-STream diffusion (DUST), a world-model augmented VLA framework that handles the modality conflict.<n>DUST achieves up to 6% gains over a standard VLA baseline and implicit world-modeling methods.<n>On real-world tasks with the Franka Research 3, DUST outperforms baselines in success rate by 13%.
  arXiv  Detail & Related papers  (2025-10-31T16:32:12Z)
• IntentionVLA: Generalizable and Efficient Embodied Intention Reasoning for Human-Robot Interaction [51.130510883952546]
  Vision-Language-Action (VLA) models leverage pretrained vision-language models (VLMs) to couple perception with robotic control.<n>We propose textbfIntentionVLA, a VLA framework with a curriculum training paradigm and an efficient inference mechanism.<n>Our proposed method first leverages carefully designed reasoning data that combine intention inference, spatial grounding, and compact embodied reasoning.
  arXiv  Detail & Related papers  (2025-10-09T04:49:46Z)
• VLA-R1: Enhancing Reasoning in Vision-Language-Action Models [35.264042764326895]
  Vision-Language-Action (VLA) models aim to unify perception, language understanding, and action generation.<n>Current VLA models often lack explicit step-by-step reasoning.<n>We present VLA-R1, a reasoning-enhanced VLA that integrates Reinforcement Learning from Verifiable Rewards.
  arXiv  Detail & Related papers  (2025-10-02T02:54:03Z)
• dVLA: Diffusion Vision-Language-Action Model with Multimodal Chain-of-Thought [66.78110237549087]
  Vision-Language-Action (VLA) models are emerging as a next-generation paradigm for robotics.<n>We introduce dVLA, a diffusion-based VLA that unifies visual perception, language reasoning, and robotic control in a single system.
  arXiv  Detail & Related papers  (2025-09-30T02:36:11Z)
• SP-VLA: A Joint Model Scheduling and Token Pruning Approach for VLA Model Acceleration [70.72227437717467]
  Vision-Language-Action (VLA) models have attracted increasing attention for their strong control capabilities.<n>Their high computational cost and low execution frequency hinder their suitability for real-time tasks such as robotic manipulation and autonomous navigation.<n>We propose SP-VLA, a unified framework that accelerates VLA models by jointly scheduling models and pruning tokens.
  arXiv  Detail & Related papers  (2025-06-15T05:04:17Z)
• Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models [30.7855782696894]
  Vision-Language-Action (VLA) models have emerged as a powerful paradigm for general-purpose robot control through natural language instructions.<n>We propose FlashVLA, the first training-free and plug-and-play acceleration framework that enables action reuse in VLA models.
  arXiv  Detail & Related papers  (2025-05-27T13:47:18Z)

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.