# Chain-of-Action: Trajectory Autoregressive Modeling for Robotic Manipulation

arXiv: https://arxiv.org/abs/2506.09990 · HTML: https://mlsanity.com/paper/2506.09990/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 48 references that are in the map.
- First posted on arXiv 11 Jun 2025.

## Builds on (most cited first, 30 of 39)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [RT-1: Robotics Transformer for Real-World Control at Scale](https://mlsanity.com/paper/2212.06817/) (2022)
- [Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware](https://mlsanity.com/paper/2304.13705/) (2023)
- [Octo: An Open-Source Generalist Robot Policy](https://mlsanity.com/paper/2405.12213/) (2024)
- [Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction](https://mlsanity.com/paper/2404.02905/) (2024)
- [Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success](https://mlsanity.com/paper/2502.19645/) (2025)
- [DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset](https://mlsanity.com/paper/2403.12945/) (2024)
- [RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation](https://mlsanity.com/paper/2410.07864/) (2024)
- [RLBench: The Robot Learning Benchmark & Learning Environment](https://mlsanity.com/paper/1909.12271/) (2019)
- [BridgeData V2: A Dataset for Robot Learning at Scale](https://mlsanity.com/paper/2308.12952/) (2023)
- [Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation](https://mlsanity.com/paper/2209.05451/) (2022)
- [BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learning](https://mlsanity.com/paper/2202.02005/) (2022)
- [CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models](https://mlsanity.com/paper/2503.22020/) (2025)
- [Better & Faster Large Language Models via Multi-token Prediction](https://mlsanity.com/paper/2404.19737/) (2024)
- [TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policies](https://mlsanity.com/paper/2412.10345/) (2024)
- [3D Diffuser Actor: Policy Diffusion with 3D Scene Representations](https://mlsanity.com/paper/2402.10885/) (2024)
- [HG-DAgger: Interactive Imitation Learning with Human Experts](https://mlsanity.com/paper/1810.02890/) (2018)
- [RVT: Robotic View Transformer for 3D Object Manipulation](https://mlsanity.com/paper/2306.14896/) (2023)
- [Any-point Trajectory Modeling for Policy Learning](https://mlsanity.com/paper/2401.00025/) (2023)
- [DART: Noise Injection for Robust Imitation Learning](https://mlsanity.com/paper/1703.09327/) (2017)
- [RVT-2: Learning Precise Manipulation from Few Demonstrations](https://mlsanity.com/paper/2406.08545/) (2024)
- [GraspVLA: a Grasping Foundation Model Pre-trained on Billion-scale Synthetic Action Data](https://mlsanity.com/paper/2505.03233/) (2025)
- [Reactive Diffusion Policy: Slow-Fast Visual-Tactile Policy Learning for Contact-Rich Manipulation](https://mlsanity.com/paper/2503.02881/) (2025)
- [RoboMamba: Efficient Vision-Language-Action Model for Robotic Reasoning and Manipulation](https://mlsanity.com/paper/2406.04339/) (2024)

## Built on by (most cited first, 17 of 17)

- [Act2Goal: From World Model To General Goal-conditioned Policy](https://mlsanity.com/paper/2512.23541/) (2025)
- [Physical Autoregressive Model for Robotic Manipulation without Action Pretraining](https://mlsanity.com/paper/2508.09822/) (2025)
- [NanoVLA: Routing Decoupled Vision-Language Understanding for Nano-sized Generalist Robotic Policies](https://mlsanity.com/paper/2510.25122/) (2025)
- [Compose Your Policies! Improving Diffusion-based or Flow-based Robot Policies via Test-time Distribution-level Composition](https://mlsanity.com/paper/2510.01068/) (2025)
- [ST4VLA: Spatially Guided Training for Vision-Language-Action Models](https://mlsanity.com/paper/2602.10109/) (2026)
- [RoboRouter: Training-Free Policy Routing for Robotic Manipulation](https://mlsanity.com/paper/2603.07892/) (2026)
- [Chain-of-Goals Hierarchical Policy for Long-Horizon Offline Goal-Conditioned RL](https://mlsanity.com/paper/2602.03389/) (2026)
- [From Imagined Futures to Executable Actions: Mixture of Latent Actions for Robot Manipulation](https://mlsanity.com/paper/2605.12167/) (2026)
- [From Failure to Feedback: Group Revision Unlocks Hard Cases in Object-Level Grounding](https://mlsanity.com/paper/2605.15951/) (2026)
- [DVG-WM: Disentangled Video Generation Enables Efficient Embodied World Model for Robotic Manipulation](https://mlsanity.com/paper/2606.32028/) (2026)
- [Agile-VLA: Few-Shot Industrial Pose Rectification via Implicit Affordance Anchoring](https://mlsanity.com/paper/2603.22899/) (2026)
- [AnchorRefine: Synergy-Manipulation Based on Trajectory Anchor and Residual Refinement for Vision-Language-Action Models](https://mlsanity.com/paper/2604.17787/) (2026)
- [Sparse Autoencoders as Plug-and-Play Firewalls for Adversarial Attack Detection in VLMs](https://mlsanity.com/paper/2605.07447/) (2026)
- [Learning New Tasks via Reusable Skills: Skill-Compositional Experts for Embodied Continual Learning](https://mlsanity.com/paper/2606.15685/) (2026)
- [LIDAR-AD: A Decoder-Free Latent-Interaction Dreamer with Action-Residual Chains for Autonomous Driving](https://mlsanity.com/paper/2607.11964/) (2026)
- [SkiP: When to Skip and When to Refine for Efficient Robot Manipulation](https://mlsanity.com/paper/2605.15536/) (2026)
- [Chunk-wise Model-based Policy Optimization](https://mlsanity.com/paper/2610.14564/) (2026)

## Abstract (arXiv)

We present Chain-of-Action (CoA), a novel visuo-motor policy paradigm built upon Trajectory Autoregressive Modeling. Unlike conventional approaches that predict next step action(s) forward, CoA generates an entire trajectory by explicit backward reasoning with task-specific goals through an action-level Chain-of-Thought (CoT) process. This process is unified within a single autoregressive structure: (1) the first token corresponds to a stable keyframe action that encodes the task-specific goals; and (2) subsequent action tokens are generated autoregressively, conditioned on the initial keyframe and previously predicted actions. This backward action reasoning enforces a global-to-local structure, allowing each local action to be tightly constrained by the final goal. To further realize the action reasoning structure, CoA incorporates four complementary designs: continuous action token representation; dynamic stopping for variable-length trajectory generation; reverse temporal ensemble; and multi-token prediction to balance action chunk modeling with global structure. As a result, CoA gives strong spatial generalization capabilities while preserving the flexibility and simplicity of a visuo-motor policy. Empirically, we observe CoA achieves the state-of-the-art performance across 60 RLBench tasks and 8 real-world manipulation tasks.