# MoRL: Reinforced Reasoning for Unified Motion Understanding and Generation

arXiv: https://arxiv.org/abs/2602.14534 · HTML: https://mlsanity.com/paper/2602.14534/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 32 of its 54 references that are in the map.
- First posted on arXiv 16 Feb 2026.

## Placed in

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

## Builds on (most cited first, 30 of 32)

- [Expressive Body Capture: 3D Hands, Face, and Body from a Single Image](https://mlsanity.com/paper/1904.05866/) (2019)
- [Human Motion Diffusion Model](https://mlsanity.com/paper/2209.14916/) (2022)
- [MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model](https://mlsanity.com/paper/2208.15001/) (2022)
- [MotionGPT: Human Motion as a Foreign Language](https://mlsanity.com/paper/2306.14795/) (2023)
- [Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model](https://mlsanity.com/paper/2503.24290/) (2025)
- [TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts](https://mlsanity.com/paper/2207.01696/) (2022)
- [The KIT Motion-Language Dataset](https://mlsanity.com/paper/1607.03827/) (2016)
- [Language2Pose: Natural Language Grounded Pose Forecasting](https://mlsanity.com/paper/1907.01108/) (2019)
- [MotionGPT: Finetuned LLMs Are General-Purpose Motion Generators](https://mlsanity.com/paper/2306.10900/) (2023)
- [Marco-o1: Towards Open Reasoning Models for Open-Ended Solutions](https://mlsanity.com/paper/2411.14405/) (2024)
- [Text2Gestures: A Transformer-Based Network for Generating Emotive Body Gestures for Virtual Agents](https://mlsanity.com/paper/2101.11101/) (2021)
- [FineMoGen: Fine-Grained Spatio-Temporal Motion Generation and Editing](https://mlsanity.com/paper/2312.15004/) (2023)
- [MotionLLM: Understanding Human Behaviors from Human Motions and Videos](https://mlsanity.com/paper/2405.20340/) (2024)
- [AvatarGPT: All-in-One Framework for Motion Understanding, Planning, Generation and Beyond](https://mlsanity.com/paper/2311.16468/) (2023)
- [Learning a bidirectional mapping between human whole-body motion and natural language using deep recurrent neural networks](https://mlsanity.com/paper/1705.06400/) (2017)
- [LaMP: Language-Motion Pretraining for Motion Generation, Retrieval, and Captioning](https://mlsanity.com/paper/2410.07093/) (2024)
- [MotionGPT-2: A General-Purpose Motion-Language Model for Motion Generation and Understanding](https://mlsanity.com/paper/2410.21747/) (2024)
- [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)
- [TextCoT: Zoom In for Enhanced Multimodal Text-Rich Image Understanding](https://mlsanity.com/paper/2404.09797/) (2024)
- [MotionChain: Conversational Motion Controllers via Multimodal Prompts](https://mlsanity.com/paper/2404.01700/) (2024)
- [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)
- [CoMA: Compositional Human Motion Generation with Multi-modal Agents](https://mlsanity.com/paper/2412.07320/) (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)
- [ReMoMask: Retrieval-Augmented Masked Motion Generation](https://mlsanity.com/paper/2508.02605/) (2025)
- [T2M-HiFiGPT: Generating High Quality Human Motion from Textual Descriptions with Residual Discrete Representations](https://mlsanity.com/paper/2312.10628/) (2023)
- [MotionRL: Align Text-to-Motion Generation to Human Preferences with Multi-Reward Reinforcement Learning](https://mlsanity.com/paper/2410.06513/) (2024)
- [SafeMo: Linguistically Grounded Unlearning for Trustworthy Text-to-Motion Generation](https://mlsanity.com/paper/2601.00590/) (2026)

## Abstract (arXiv)

Human motion understanding and generation are crucial for vision and robotics but remain limited in reasoning capability and test-time planning. We propose MoRL, a unified multimodal motion model trained with supervised fine-tuning and reinforcement learning with verifiable rewards. Our task-specific reward design combines semantic alignment and reasoning coherence for understanding with physical plausibility and text-motion consistency for generation, improving both logical reasoning and perceptual realism. To further enhance inference, we introduce Chain-of-Motion (CoM), a test-time reasoning method that enables step-by-step planning and reflection. We also construct two large-scale CoT datasets, MoUnd-CoT-140K and MoGen-CoT-140K, to align motion sequences with reasoning traces and action descriptions. Experiments on HumanML3D and KIT-ML show that MoRL achieves significant gains over state-of-the-art baselines. Code: https://github.com/AIGeeksGroup/MoRL. Website: https://aigeeksgroup.github.io/MoRL.