# Don't Throw Away the Tail: Action Upcycling for Policy Acceleration

arXiv: https://arxiv.org/abs/2609.34911 · HTML: https://mlsanity.com/paper/2609.34911/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 27 references that are in the map.
- First posted on arXiv 28 Sep 2026.

## Builds on (most cited first, 26 of 26)

- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [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)
- [Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware](https://mlsanity.com/paper/2304.13705/) (2023)
- [LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning](https://mlsanity.com/paper/2306.03310/) (2023)
- [GR00T N1: An Open Foundation Model for Generalist Humanoid Robots](https://mlsanity.com/paper/2503.14734/) (2025)
- [SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics](https://mlsanity.com/paper/2506.01844/) (2025)
- [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)
- [Fast-WAM: Do World Action Models Need Test-time Future Imagination?](https://mlsanity.com/paper/2603.16666/) (2026)
- [LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models](https://mlsanity.com/paper/2510.13626/) (2025)
- [Motus: A Unified Latent Action World Model](https://mlsanity.com/paper/2512.13030/) (2025)
- [Real-Time Execution of Action Chunking Flow Policies](https://mlsanity.com/paper/2506.07339/) (2025)
- [Consistency Policy: Accelerated Visuomotor Policies via Consistency Distillation](https://mlsanity.com/paper/2405.07503/) (2024)
- [π0.7: a Steerable Generalist Robotic Foundation Model with Emergent Capabilities](https://mlsanity.com/paper/2604.15483/) (2026)
- [DeeR-VLA: Dynamic Inference of Multimodal Large Language Models for Efficient Robot Execution](https://mlsanity.com/paper/2411.02359/) (2024)
- [EfficientVLA: Training-Free Acceleration and Compression for Vision-Language-Action Models](https://mlsanity.com/paper/2506.10100/) (2025)
- [One-Step Diffusion Policy: Fast Visuomotor Policies via Diffusion Distillation](https://mlsanity.com/paper/2410.21257/) (2024)
- [VLA-Cache: Efficient Vision-Language-Action Manipulation via Adaptive Token Caching](https://mlsanity.com/paper/2502.02175/) (2025)
- [Bidirectional Decoding: Improving Action Chunking via Guided Test-Time Sampling](https://mlsanity.com/paper/2408.17355/) (2024)
- [Adaptive Action Chunking at Inference-time for Vision-Language-Action Models](https://mlsanity.com/paper/2604.04161/) (2026)
- [Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference](https://mlsanity.com/paper/2511.16449/) (2025)
- [Why Does Action Chunking Improve Behavioral Cloning Performance in Robotic Control?](https://mlsanity.com/paper/2608.02547/) (2026)
- [FlashVLA: Streaming Action Decoding for Fast and Asynchronous VLA Inference](https://mlsanity.com/paper/2608.27384/) (2026)
- [Knowing When to Stop: Adaptive Action Chunking via Internal Cross-Attention Dynamics in VLAs](https://mlsanity.com/paper/2609.00908/) (2026)
- [Dynamic Execution Commitment of Vision-Language-Action Models](https://mlsanity.com/paper/2605.11567/) (2026)
- [Revisiting Open-Loop Execution in Robotics: Toward Reactive, Higher-Performing Policies](https://mlsanity.com/paper/2608.15938/) (2026)

## Abstract (arXiv)

Modern robot policies predict a chunk of future actions from a single observation, execute only a prefix, and discard the rest before replanning. Choosing the length of this prefix, the execution horizon, poses a trade-off between reactivity and efficiency. A short horizon keeps the policy reactive to the environment, but requires frequent policy calls. Recent test-time methods adaptively select the horizon for each chunk, but they either read model internals, where the signal must be chosen for each architecture, or draw extra samples, which adds cost. We propose Action Upcycling, a training-free algorithm that reuses actions the policy would otherwise discard, without accessing model internals or drawing extra samples. We find that discarded actions stay close to their replanned versions as long as the action velocity remains smooth. Action Upcycling therefore extends the execution horizon up to the point where the velocity begins to fluctuate. Extensive experiments on simulated and real-world manipulation tasks show that Action Upcycling reduces policy calls by 1.2-1.7x with no loss in success rate, across multiple Vision-Language-Action Models (VLAs) and even a World Action Model (WAM). It applies to any chunked policy at negligible cost and is orthogonal to other policy acceleration methods such as few-step sampling and streaming action decoding, opening a new axis for policy acceleration.