# Action-Free Reasoning for Policy Generalization

arXiv: https://arxiv.org/abs/2502.03729 · HTML: https://mlsanity.com/paper/2502.03729/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Placed in Robot manipulation imitation learning, one of 13 directions in Offline RL and imitation learning from data.
- First posted on arXiv 6 Feb 2025.

## Placed in

- Offline RL and imitation learning from data / [Robot manipulation imitation learning](https://mlsanity.com/offlinerl/robot-manipulation-imitation-learning/)

## Built on by (most cited first, 26 of 26)

- [Motus: A Unified Latent Action World Model](https://mlsanity.com/paper/2512.13030/) (2025)
- [Unified Video Action Model](https://mlsanity.com/paper/2503.00200/) (2025)
- [ThinkAct: Vision-Language-Action Reasoning via Reinforced Visual Latent Planning](https://mlsanity.com/paper/2507.16815/) (2025)
- [Controllable Video Generation: A Survey](https://mlsanity.com/paper/2507.16869/) (2025)
- [A Survey on Vision-Language-Action Models: An Action Tokenization Perspective](https://mlsanity.com/paper/2507.01925/) (2025)
- [InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policy](https://mlsanity.com/paper/2510.13778/) (2025)
- [Being-H0.7: A Latent World-Action Model from Egocentric Videos](https://mlsanity.com/paper/2605.00078/) (2026)
- [Being-H0.5: Scaling Human-Centric Robot Learning for Cross-Embodiment Generalization](https://mlsanity.com/paper/2601.12993/) (2026)
- [RoboMonkey: Scaling Test-Time Sampling and Verification for Vision-Language-Action Models](https://mlsanity.com/paper/2506.17811/) (2025)
- [InternVLA-A1: Unifying Understanding, Generation and Action for Robotic Manipulation](https://mlsanity.com/paper/2601.02456/) (2026)
- [Robot-R1: Reinforcement Learning for Enhanced Embodied Reasoning in Robotics](https://mlsanity.com/paper/2506.00070/) (2025)
- [Generative AI Act II: Test Time Scaling Drives Cognition Engineering](https://mlsanity.com/paper/2504.13828/) (2025)
- [ST4VLA: Spatially Guided Training for Vision-Language-Action Models](https://mlsanity.com/paper/2602.10109/) (2026)
- [Survey of Vision-Language-Action Models for Embodied Manipulation](https://mlsanity.com/paper/2508.15201/) (2025)
- [Learning Primitive Embodied World Models: Towards Scalable Robotic Learning](https://mlsanity.com/paper/2508.20840/) (2025)
- [Robot Learning from Human Videos: A Survey](https://mlsanity.com/paper/2604.27621/) (2026)
- [DextER: Language-driven Dexterous Grasp Generation with Embodied Reasoning](https://mlsanity.com/paper/2601.16046/) (2026)
- [EVE: A Generator-Verifier System for Generative Policies](https://mlsanity.com/paper/2512.21430/) (2025)
- [Self-Supervised Bootstrapping of Action-Predictive Embodied Reasoning](https://mlsanity.com/paper/2602.08167/) (2026)
- [From Imagined Futures to Executable Actions: Mixture of Latent Actions for Robot Manipulation](https://mlsanity.com/paper/2605.12167/) (2026)
- [E-TTS: A New Embodied Test-Time Scaling Framework for Robotic Manipulation](https://mlsanity.com/paper/2606.27268/) (2026)
- [Cross-Embodiment Transfer via Behavior-Aligned Representations](https://mlsanity.com/paper/2607.27549/) (2026)
- [Evolve Vision-Language-Action Model into an Agent with On-the-fly Tool-use](https://mlsanity.com/paper/2608.14047/) (2026)
- [Inductive Generalization for Robotic Manipulation](https://mlsanity.com/paper/2606.20999/) (2026)
- [LeapBot-WA: World-Anchor Action Models via Predictive Latent Alignments](https://mlsanity.com/paper/2607.23969/) (2026)
- [EgoLAP: Learning from Egocentric Human Data through Language-Action Reasoning](https://mlsanity.com/paper/2610.08726/) (2026)

## Abstract (arXiv)

End-to-end imitation learning offers a promising approach for training robot policies. However, generalizing to new settings remains a significant challenge. Although large-scale robot demonstration datasets have shown potential for inducing generalization, they are resource-intensive to scale. In contrast, human video data is abundant and diverse, presenting an attractive alternative. Yet, these human-video datasets lack action labels, complicating their use in imitation learning. Existing methods attempt to extract grounded action representations (e.g., hand poses), but resulting policies struggle to bridge the embodiment gap between human and robot actions. We propose an alternative approach: leveraging language-based reasoning from human videos-essential for guiding robot actions-to train generalizable robot policies. Building on recent advances in reasoning-based policy architectures, we introduce Reasoning through Action-free Data (RAD). RAD learns from both robot demonstration data (with reasoning and action labels) and action-free human video data (with only reasoning labels). The robot data teaches the model to map reasoning to low-level actions, while the action-free data enhances reasoning capabilities. Additionally, we will release a new dataset of 3,377 human-hand demonstrations with reasoning annotations compatible with the Bridge V2 benchmark and aimed at facilitating future research on reasoning-driven robot learning. Our experiments show that RAD enables effective transfer across the embodiment gap, allowing robots to perform tasks seen only in action-free data. Furthermore, scaling up action-free reasoning data significantly improves policy performance and generalization to novel tasks. These results highlight the promise of reasoning-driven learning from action-free datasets for advancing generalizable robot control. Project page: https://rad-generalization.github.io