# Motion-R1: Enhancing Motion Generation with Decomposed Chain-of-Thought and RL Binding

arXiv: https://arxiv.org/abs/2506.10353 · HTML: https://mlsanity.com/paper/2506.10353/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 19 of its 61 references that are in the map.
- First posted on arXiv 12 Jun 2025.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)

## Builds on (most cited first, 19 of 19)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model](https://mlsanity.com/paper/2208.15001/) (2022)
- [MotionCLIP: Exposing Human Motion Generation to CLIP Space](https://mlsanity.com/paper/2203.08063/) (2022)
- [Human Motion Diffusion as a Generative Prior](https://mlsanity.com/paper/2303.01418/) (2023)
- [Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement](https://mlsanity.com/paper/2503.06520/) (2025)
- [MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learning](https://mlsanity.com/paper/2502.19634/) (2025)
- [Reason-RFT: Reinforcement Fine-Tuning for Visual Reasoning of Vision Language Models](https://mlsanity.com/paper/2503.20752/) (2025)
- [Motion-Agent: A Conversational Framework for Human Motion Generation with LLMs](https://mlsanity.com/paper/2405.17013/) (2024)
- [Motion Anything: Any to Motion Generation](https://mlsanity.com/paper/2503.06955/) (2025)
- [TEILP: Time Prediction over Knowledge Graphs via Logical Reasoning](https://mlsanity.com/paper/2312.15816/) (2023)
- [InfiniMotion: Mamba Boosts Memory in Transformer for Arbitrary Long Motion Generation](https://mlsanity.com/paper/2407.10061/) (2024)
- [Motion Avatar: Generate Human and Animal Avatars with Arbitrary Motion](https://mlsanity.com/paper/2405.11286/) (2024)
- [Aligning Human Motion Generation with Human Perceptions](https://mlsanity.com/paper/2407.02272/) (2024)
- [KMM: Key Frame Mask Mamba for Extended Motion Generation](https://mlsanity.com/paper/2411.06481/) (2024)
- [InfiniDreamer: Arbitrarily Long Human Motion Generation via Segment Score Distillation](https://mlsanity.com/paper/2411.18303/) (2024)

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

- [Affordance-R1: Reinforcement Learning for Generalizable Affordance Reasoning in Multimodal Large Language Model](https://mlsanity.com/paper/2508.06206/) (2025)
- [Object Detection with Multimodal Large Vision-Language Models: An In-depth Review](https://mlsanity.com/paper/2508.19294/) (2025)
- [MM-R1: Unleashing the Power of Unified Multimodal Large Language Models for Personalized Image Generation](https://mlsanity.com/paper/2508.11433/) (2025)
- [UniMo: Unified Motion Generation and Understanding with Chain of Thought](https://mlsanity.com/paper/2601.12126/) (2026)
- [HOID-R1: Reinforcement Learning for Open-World Human-Object Interaction Detection Reasoning with Multimodal Large Language Model](https://mlsanity.com/paper/2508.11350/) (2025)
- [UniMesh: Unifying 3D Mesh Understanding and Generation](https://mlsanity.com/paper/2604.17472/) (2026)
- [PartRAG: Retrieval-Augmented Part-Level 3D Generation and Editing](https://mlsanity.com/paper/2602.17033/) (2026)
- [Beyond MoCap: Scaling Motion Tokenizers with Synthetic Human Motion for Generative Modeling](https://mlsanity.com/paper/2606.27547/) (2026)
- [Human-Centric Intelligence in the Era of Foundation Models: A Survey](https://mlsanity.com/paper/2608.18184/) (2026)

## Abstract (arXiv)

Text-to-Motion generation has become a fundamental task in human-machine interaction, enabling the synthesis of realistic human motions from natural language descriptions. Although recent advances in large language models and reinforcement learning have contributed to high-quality motion generation, two major challenges remain. Existing approaches often fail to capture the temporal and causal complexities inherent in natural language, leading to oversimplified or incoherent motions. Additionally, RL-based methods are frequently overly complex, hindering their scalability and adaptability across various motion generation tasks. To address these challenges, we propose Motion-R1, a novel framework that combines decomposed Chain-of-Thought reasoning with reinforcement learning to enhance both the quality and interpretability of generated motions. Specifically, we introduce the Decomposed CoT Data Engine, which leverages an automated pipeline to synthesize high-quality reasoning data, allowing the model to better capture the temporal dependencies and causal relationships of human motion. We also propose RL Binding, a reinforcement learning strategy that incorporates multi-modal text-motion alignment into the RL reward function, guiding the model to produce motions that are both semantically accurate and motionally realistic. Extensive experiments across benchmark datasets demonstrate that Motion-R1 achieves state-of-the-art performance, with a 3.5% improvement in MM-Dist on HumanML3D and improvements in R-Precision and FID on KIT-ML and BABEL, surpassing existing methods across key metrics and highlighting its superior capability in handling complex motion generation tasks. Project page: https://motion-r1.github.io/.