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

arXiv: https://arxiv.org/abs/2602.09849 · HTML: https://mlsanity.com/paper/2602.09849/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning and chain-of-thought in VLA, one of 13 directions in Vision-language-action models.
- Builds on 36 of its 45 references that are in the map.
- First posted on arXiv 10 Feb 2026.

## Placed in

- Vision-language-action models / [Reasoning and chain-of-thought in VLA](https://mlsanity.com/vla/reasoning-and-chain-of-thought-in-vla/)

## Builds on (most cited first, 30 of 36)

- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow](https://mlsanity.com/paper/2209.03003/) (2022)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025)
- [SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features](https://mlsanity.com/paper/2502.14786/) (2025)
- [Chameleon: Mixed-Modal Early-Fusion Foundation Models](https://mlsanity.com/paper/2405.09818/) (2024)
- [Emerging Properties in Unified Multimodal Pretraining](https://mlsanity.com/paper/2505.14683/) (2025)
- [Show-o: One Single Transformer to Unify Multimodal Understanding and Generation](https://mlsanity.com/paper/2408.12528/) (2024)
- [RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation](https://mlsanity.com/paper/2410.07864/) (2024)
- [BridgeData V2: A Dataset for Robot Learning at Scale](https://mlsanity.com/paper/2308.12952/) (2023)
- [CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks](https://mlsanity.com/paper/2112.03227/) (2021)
- [Learning Universal Policies via Text-Guided Video Generation](https://mlsanity.com/paper/2302.00111/) (2023)
- [RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation](https://mlsanity.com/paper/2506.18088/) (2025)
- [Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning](https://mlsanity.com/paper/2601.16163/) (2026)
- [GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulation](https://mlsanity.com/paper/2410.06158/) (2024)
- [Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations](https://mlsanity.com/paper/2412.14803/) (2024)
- [3D Diffuser Actor: Policy Diffusion with 3D Scene Representations](https://mlsanity.com/paper/2402.10885/) (2024)
- [Show-o2: Improved Native Unified Multimodal Models](https://mlsanity.com/paper/2506.15564/) (2025)
- [DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge](https://mlsanity.com/paper/2507.04447/) (2025)
- [EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video](https://mlsanity.com/paper/2505.11709/) (2025)
- [mimic-video: Video-Action Models for Generalizable Robot Control Beyond VLAs](https://mlsanity.com/paper/2512.15692/) (2025)
- [LMFusion: Adapting Pretrained Language Models for Multimodal Generation](https://mlsanity.com/paper/2412.15188/) (2024)
- [UP-VLA: A Unified Understanding and Prediction Model for Embodied Agent](https://mlsanity.com/paper/2501.18867/) (2025)
- [Gemini Robotics 1.5: Pushing the Frontier of Generalist Robots with Advanced Embodied Reasoning, Thinking, and Motion Transfer](https://mlsanity.com/paper/2510.03342/) (2025)
- [F1: A Vision-Language-Action Model Bridging Understanding and Generation to Actions](https://mlsanity.com/paper/2509.06951/) (2025)
- [Zebra-CoT: A Dataset for Interleaved Vision Language Reasoning](https://mlsanity.com/paper/2507.16746/) (2025)

## Built on by (most cited first, 30 of 30)

- [Unified 4D World Action Modeling from Video Priors with Asynchronous Denoising](https://mlsanity.com/paper/2604.26694/) (2026)
- [World Model for Robot Learning: A Comprehensive Survey](https://mlsanity.com/paper/2605.00080/) (2026)
- [ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing?](https://mlsanity.com/paper/2606.19531/) (2026)
- [Disentangled Robot Learning via Separate Forward and Inverse Dynamics Pretraining](https://mlsanity.com/paper/2604.16391/) (2026)
- [T-Rex: Tactile-Reactive Dexterous Manipulation](https://mlsanity.com/paper/2606.17055/) (2026)
- [World Action Models: A Survey](https://mlsanity.com/paper/2606.20781/) (2026)
- [Long-Horizon Manipulation via Trace-Conditioned VLA Planning](https://mlsanity.com/paper/2604.21924/) (2026)
- [DreamWAM: Beyond RGB Future Prediction for World Action Models](https://mlsanity.com/paper/2608.04996/) (2026)
- [MV-WAM: Manifold-Aware World Action Model with Value Augmentation](https://mlsanity.com/paper/2606.21088/) (2026)
- [StatePlay: State-Aware Game World Models for Mechanics-Consistent Generation](https://mlsanity.com/paper/2607.26754/) (2026)
- [FACT: Failure-Aware Causal Training for World-Action Models](https://mlsanity.com/paper/2608.10232/) (2026)
- [Veo-Act: Enhancing VLA Policies with Frontier Video Models](https://mlsanity.com/paper/2604.04502/) (2026)
- [UAM: A Dual-Stream Perspective on Forgetting in VLA Training](https://mlsanity.com/paper/2605.15735/) (2026)
- [FoMoVLA: Bridging Visual Foresight and Motion Guidance for Vision-Language-Action Models](https://mlsanity.com/paper/2607.14739/) (2026)
- [Towards Physics of Multimodal Pretraining: Knowledge Flow, Modality Synergy, Early Unification, and Recipes](https://mlsanity.com/paper/2608.05000/) (2026)
- [RxBrain: Embodied Cognition Foundation Model with Joint Language-Visual Reasoning and Imagination](https://mlsanity.com/paper/2607.14187/) (2026)
- [Beyond Dense Futures: World Models as Structured Planners for Robotic Manipulation](https://mlsanity.com/paper/2603.12553/) (2026)
- [Safe Embodied AI for Long-horizon Tasks: A Cross-layer Analysis of Robotic Manipulation](https://mlsanity.com/paper/2606.05660/) (2026)
- [ThinkingVLA: Interleaved Vision and Language Reasoning for Robotic Manipulation](https://mlsanity.com/paper/2606.17937/) (2026)
- [UniMPA: A Unified Memory-Prediction-Action Model via Action-Grounded Transition Modeling](https://mlsanity.com/paper/2609.11875/) (2026)
- [MachEmbodied-U0: Unified Understanding and Generation Model for Embodied Intelligence](https://mlsanity.com/paper/2609.25627/) (2026)
- [WorldBagel: Uncovering the Power of Unified Multimodal Models for Vision-Language-Action-World Modeling](https://mlsanity.com/paper/2607.03461/) (2026)
- [APIVOT: Adaptive Planning with Interleaved Vision-Language Thoughts](https://mlsanity.com/paper/2607.08024/) (2026)
- [Toward Unified Robot Learning: Bridging Representation, Vision-Language-Action, and World Models](https://mlsanity.com/paper/2609.03927/) (2026)
- [MT-WAM: Reorienting the One-Pass Predictive Representation Toward Action Generation](https://mlsanity.com/paper/2609.21474/) (2026)
- [Enabling a Unified Cross-Domain Representation for Two-Finger Gripper Manipulation via Interaction-Centric Modeling](https://mlsanity.com/paper/2609.31207/) (2026)
- [World Action Modeling with Progressive Visual Planning](https://mlsanity.com/paper/2610.02508/) (2026)
- [Native Action-Prior Learning from Videos for World Action Models](https://mlsanity.com/paper/2610.03391/) (2026)
- [Rewiring Semantics, Dynamics, and Control: A Simple yet Effective Action-Centric Tri-Stream Transformer](https://mlsanity.com/paper/2610.11416/) (2026)
- [What Matters for World Modeling in Vision-Language-Action Models?](https://mlsanity.com/paper/2610.19825/) (2026)

## Abstract (arXiv)

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.