# Compose Your Policies! Improving Diffusion-based or Flow-based Robot Policies via Test-time Distribution-level Composition

arXiv: https://arxiv.org/abs/2510.01068 · HTML: https://mlsanity.com/paper/2510.01068/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning and post-training, one of 13 directions in Vision-language-action models.
- Builds on 75 of its 186 references that are in the map.
- First posted on arXiv 1 Oct 2025.

## Placed in

- Vision-language-action models / [Reinforcement learning and post-training](https://mlsanity.com/vla/reinforcement-learning-and-post-training/)
- Diffusion models / [Diffusion and flow policies for robotics](https://mlsanity.com/diffusion/diffusion-and-flow-policies-for-robotics/)

## Builds on (most cited first, 30 of 75)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [Octo: An Open-Source Generalist Robot Policy](https://mlsanity.com/paper/2405.12213/) (2024)
- [GR00T N1: An Open Foundation Model for Generalist Humanoid Robots](https://mlsanity.com/paper/2503.14734/) (2025)
- [RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation](https://mlsanity.com/paper/2410.07864/) (2024)
- [FAST: Efficient Action Tokenization for Vision-Language-Action Models](https://mlsanity.com/paper/2501.09747/) (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)
- [Is Conditional Generative Modeling all you need for Decision-Making?](https://mlsanity.com/paper/2211.15657/) (2022)
- [CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation](https://mlsanity.com/paper/2411.19650/) (2024)
- [AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems](https://mlsanity.com/paper/2503.06669/) (2025)
- [Latent Action Pretraining from Videos](https://mlsanity.com/paper/2410.11758/) (2024)
- [Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations](https://mlsanity.com/paper/2412.14803/) (2024)
- [Rectified Flow: A Marginal Preserving Approach to Optimal Transport](https://mlsanity.com/paper/2209.14577/) (2022)
- [A Survey on Vision-Language-Action Models for Embodied AI](https://mlsanity.com/paper/2405.14093/) (2024)
- [Diffusion Policy Policy Optimization](https://mlsanity.com/paper/2409.00588/) (2024)
- [NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigation](https://mlsanity.com/paper/2402.15852/) (2024)
- [NaVILA: Legged Robot Vision-Language-Action Model for Navigation](https://mlsanity.com/paper/2412.04453/) (2024)
- [RT-H: Action Hierarchies Using Language](https://mlsanity.com/paper/2403.01823/) (2024)
- [Unified Video Action Model](https://mlsanity.com/paper/2503.00200/) (2025)
- [HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Model](https://mlsanity.com/paper/2503.10631/) (2025)
- [Scaling Robot Learning with Semantically Imagined Experience](https://mlsanity.com/paper/2302.11550/) (2023)
- [Steering Your Diffusion Policy with Latent Space Reinforcement Learning](https://mlsanity.com/paper/2506.15799/) (2025)
- [Language-Driven Representation Learning for Robotics](https://mlsanity.com/paper/2302.12766/) (2023)
- [Knowledge Insulating Vision-Language-Action Models: Train Fast, Run Fast, Generalize Better](https://mlsanity.com/paper/2505.23705/) (2025)
- [A Careful Examination of Large Behavior Models for Multitask Dexterous Manipulation](https://mlsanity.com/paper/2507.05331/) (2025)
- [ChatVLA: Unified Multimodal Understanding and Robot Control with Vision-Language-Action Model](https://mlsanity.com/paper/2502.14420/) (2025)

## Built on by (most cited first, 9 of 9)

- [DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos](https://mlsanity.com/paper/2602.06949/) (2026)
- [VLS: Steering Pretrained Robot Policies via Vision-Language Models](https://mlsanity.com/paper/2602.03973/) (2026)
- [Breaking Lock-In: Preserving Steerability under Low-Data VLA Post-Training](https://mlsanity.com/paper/2604.23121/) (2026)
- [AttenA+: Rectifying Action Inequality in Robotic Foundation Models](https://mlsanity.com/paper/2605.13548/) (2026)
- [Factored Diffusion Policies:Compositionally Generalized Robot Control with a Single Score Network](https://mlsanity.com/paper/2605.22596/) (2026)
- [Asynchronous Multimodal Diffusion Policy Composition via Latency-Aware Guidance Fusion](https://mlsanity.com/paper/2607.17257/) (2026)
- [Liquid Networks with Mixture Density Heads for Efficient Imitation Learning](https://mlsanity.com/paper/2603.27058/) (2026)
- [Closed-Loop Neural Activation Control in Vision-Language-Action Models](https://mlsanity.com/paper/2606.00269/) (2026)
- [Encoded but Not in Control: Revealing the Grounding Gap in Vision-Language Robot Policies](https://mlsanity.com/paper/2610.06235/) (2026)

## Abstract (arXiv)

Diffusion-based models for robotic control, including vision-language-action (VLA) and vision-action (VA) policies, have demonstrated significant capabilities. Yet their advancement is constrained by the high cost of acquiring large-scale interaction datasets. This work introduces an alternative paradigm for enhancing policy performance without additional model training. Perhaps surprisingly, we demonstrate that the composed policies can exceed the performance of either parent policy. Our contribution is threefold. First, we establish a theoretical foundation showing that the convex composition of distributional scores from multiple diffusion models can yield a superior one-step functional objective compared to any individual score. A Gr"onwall-type bound is then used to show that this single-step improvement propagates through entire generation trajectories, leading to systemic performance gains. Second, motivated by these results, we propose General Policy Composition (GPC), a training-free method that enhances performance by combining the distributional scores of multiple pre-trained policies via a convex combination and test-time search. GPC is versatile, allowing for the plug-and-play composition of heterogeneous policies, including VA and VLA models, as well as those based on diffusion or flow-matching, irrespective of their input visual modalities. Third, we provide extensive empirical validation. Experiments on Robomimic, PushT, and RoboTwin benchmarks, alongside real-world robotic evaluations, confirm that GPC consistently improves performance and adaptability across a diverse set of tasks. Further analysis of alternative composition operators and weighting strategies offers insights into the mechanisms underlying the success of GPC. These results establish GPC as a simple yet effective method for improving control performance by leveraging existing policies.