BagelVLA: Enhancing Long-Horizon Manipulation via Interleaved Vision-Language-Action Generation

• URL: http://arxiv.org/abs/2602.09849v2
• Date: Wed, 11 Feb 2026 03:54:17 GMT
• Title: BagelVLA: Enhancing Long-Horizon Manipulation via Interleaved Vision-Language-Action Generation
• Abstract summary: Vision-Language-Action (VLA) models typically focus on either linguistic planning or visual forecasting in isolation.<n>We propose BagelVLA, a unified model that integrates linguistic planning, visual forecasting, and action generation within a single framework.<n>Extensive experiments demonstrate that BagelVLA outperforms existing baselines on multiple simulated and real-world benchmarks.
• Score: 14.657523625592658
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Equipping embodied agents with the ability to reason about tasks, foresee physical outcomes, and generate precise actions is essential for general-purpose manipulation. While recent Vision-Language-Action (VLA) models have leveraged pre-trained foundation models, they typically focus on either linguistic planning or visual forecasting in isolation. These methods rarely integrate both capabilities simultaneously to guide action generation, leading to suboptimal performance in complex, long-horizon manipulation tasks. To bridge this gap, we propose BagelVLA, a unified model that integrates linguistic planning, visual forecasting, and action generation within a single framework. Initialized from a pretrained unified understanding and generative model, BagelVLA is trained to interleave textual reasoning and visual prediction directly into the action execution loop. To efficiently couple these modalities, we introduce Residual Flow Guidance (RFG), which initializes from current observation and leverages single-step denoising to extract predictive visual features, guiding action generation with minimal latency. Extensive experiments demonstrate that BagelVLA outperforms existing baselines by a significant margin on multiple simulated and real-world benchmarks, particularly in tasks requiring multi-stage reasoning.

Related papers

• TS-Mask VLA: 2D Temporal-Spatial Masking for Vision-Language-Action Model with Effective Bridging [18.666233973595762]
  TS-Mask VLA is a vision-language-action framework for robot manipulation.<n>It is built upon two key designs: (1) a Discrete Action Expert equipped with a Bridge Attention conditioning bridge and (2) a temporal-spatial 2D masking strategy.<n>It achieves a 9 percent average success rate with only 0.5B parameters, outperforming significantly larger models.
  arXiv  Detail & Related papers  (2026-07-10T07:06:02Z)
• QuoVLA: Quotient Space for Vision-Language-Action Models [51.02329790939691]
  Vision-Language-Action (VLA) models commonly adapt pretrained VLM latents to robot control by mapping visual observations and language instructions to continuous actions.<n>Our textitQuotient Theory for VLA shows that pretrained VLM latents are not action-insufficient but action-sufficient.<n>We propose QuoVLA, a quotient-space framework for VLA that compresses pretrained VLM latents into action-sufficient representations.
  arXiv  Detail & Related papers  (2026-05-24T06:28:53Z)
• Afford-VLA: Action-Aligned Visual Planning via Internalized Affordance [108.46436073194546]
  We argue that effective planning should be local, visually grounded, internally generated, and directly aligned with action.<n>We propose Afford-VLA, a unified framework that internalizes task-conditioned affordance as an explicit visual planning interface within VLA models.
  arXiv  Detail & Related papers  (2026-05-22T20:43:47Z)
• LoopVLA: Learning Sufficiency in Recurrent Refinement for Vision-Language-Action Models [13.30873593845724]
  LoopVLA is a recurrent Vision-Language-Action architecture that learns representation refinement, action prediction, and sufficiency estimation.<n>We show that LoopVLA pushes the efficiency-performance frontier of VLA policies, reducing parameters by 45% and improving inference throughput by up to 1.7 times.
  arXiv  Detail & Related papers  (2026-05-11T03:51:22Z)
• VLA-IAP: Training-Free Visual Token Pruning via Interaction Alignment for Vision-Language-Action Models [27.12266806191131]
  Vision-Language-Action (VLA) models have rapidly advanced embodied intelligence, enabling robots to execute complex, instruction-driven tasks.<n>Current approaches often prune visually sparse yet structurally critical regions that support manipulation, leading to unstable behavior during early task phases.<n>Our proposed textbftraining-free method, VLA-IAP (Interaction-Aligned Pruning), introduces a geometric prior mechanism to preserve structural anchors and a dynamic scheduling strategy.
  arXiv  Detail & Related papers  (2026-03-24T09:33:05Z)
• 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)
• ActDistill: General Action-Guided Self-Derived Distillation for Efficient Vision-Language-Action Models [14.202025149504715]
  We present ActDistill, a framework that transfers the action prediction capability of any existing VLA model to a lightweight counterpart.<n>We employ a well-trained VLA model as the teacher and introduce a graph-structured encapsulation strategy to explicitly model the hierarchical evolution of action prediction.<n>Experiments on embodied benchmarks demonstrate that ActDistill achieves comparable or superior performance to full-scale VLA models while reducing computation by over 50% with up to 1.67 times speedup.
  arXiv  Detail & Related papers  (2025-11-22T14:44:03Z)
• Unified Diffusion VLA: Vision-Language-Action Model via Joint Discrete Denoising Diffusion Process [48.63424123606625]
  Vision-language-action (VLA) models aim to understand natural language instructions and visual observations.<n>Recent work integrates future images into the understanding-acting loop, yielding unified VLAs that jointly understand, generate, and act.<n>We propose a two-stage training pipeline and several inference-time techniques that optimize performance and efficiency.
  arXiv  Detail & Related papers  (2025-11-03T16:26:54Z)
• Do What You Say: Steering Vision-Language-Action Models via Runtime Reasoning-Action Alignment Verification [17.948161564138033]
  Reasoning Vision Language Action (VLA) models improve robotic instruction-following by generating step-by-step textual plans before low-level actions.<n>But even with a correct textual plan, the generated actions can still miss the intended outcomes in the plan, especially in out-of-distribution scenarios.<n>We formalize this phenomenon as a lack of embodied CoT faithfulness, and introduce a training-free, runtime policy steering method for reasoning-action alignment.
  arXiv  Detail & Related papers  (2025-10-18T00:38:45Z)
• Hybrid Training for Vision-Language-Action Models [10.451756630631609]
  We propose a framework that enables Vision-Language-Action models to learn from thoughts and benefit from associated performance gains.<n>By learning to conditionally predict a diverse set of outputs, HyT supports flexibility at inference time, enabling the model to either predict actions directly, generate thoughts or follow instructions.
  arXiv  Detail & Related papers  (2025-10-01T07:27:15Z)
• CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models [89.44024245194315]
  We introduce a method that incorporates explicit visual chain-of-thought (CoT) reasoning into vision-language-action models (VLAs)<n>We introduce CoT-VLA, a state-of-the-art 7B VLA that can understand and generate visual and action tokens.<n>Our experimental results demonstrate that CoT-VLA achieves strong performance, outperforming the state-of-the-art VLA model by 17% in real-world manipulation tasks and 6% in simulation benchmarks.
  arXiv  Detail & Related papers  (2025-03-27T22:23:04Z)
• HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Model [54.64088247291416]
  A fundamental objective of manipulation policy design is to endow robots to comprehend human instructions, reason about scene cues, and execute generalized actions in dynamic environments.<n>Recent autoregressive vision-language-action (VLA) methods inherit common-sense reasoning capabilities from vision-language models (VLMs) for next action-token prediction.<n>We introduce HybridVLA, a unified framework that absorbs the continuous nature of diffusion-based actions and the contextual reasoning of autoregression.
  arXiv  Detail & Related papers  (2025-03-13T17:59:52Z)
• SimVLM: Simple Visual Language Model Pretraining with Weak Supervision [48.98275876458666]
  We present a minimalist pretraining framework, named Simple Visual Language Model (SimVLM) SimVLM reduces the training complexity by exploiting large-scale weak supervision. It achieves new state-of-the-art results on a wide range of discriminative and generative vision-language benchmarks.
  arXiv  Detail & Related papers  (2021-08-24T18:14:00Z)

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.