# EBT-Policy: Energy Unlocks Emergent Physical Reasoning Capabilities

arXiv: https://arxiv.org/abs/2510.27545 · HTML: https://mlsanity.com/paper/2510.27545/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 8 of its 59 references that are in the map.
- First posted on arXiv 31 Oct 2025.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)
- Vision-language-action models / [Human-video and latent-action pretraining](https://mlsanity.com/vla/human-video-and-latent-action-pretraining/)
- Diffusion models / [Diffusion and flow policies for robotics](https://mlsanity.com/diffusion/diffusion-and-flow-policies-for-robotics/)

## Builds on (most cited first, 8 of 8)

- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Training Large Language Models to Reason in a Continuous Latent Space](https://mlsanity.com/paper/2412.06769/) (2024)
- [Unified Video Action Model](https://mlsanity.com/paper/2503.00200/) (2025)
- [Improved Contrastive Divergence Training of Energy Based Models](https://mlsanity.com/paper/2012.01316/) (2020)
- [Scaling Cross-Embodied Learning: One Policy for Manipulation, Navigation, Locomotion and Aviation](https://mlsanity.com/paper/2408.11812/) (2024)
- [Visual Whole-Body Control for Legged Loco-Manipulation](https://mlsanity.com/paper/2403.16967/) (2024)
- [Learning Iterative Reasoning through Energy Diffusion](https://mlsanity.com/paper/2406.11179/) (2024)
- [Get Back Here: Robust Imitation by Return-to-Distribution Planning](https://mlsanity.com/paper/2305.01400/) (2023)

## Built on by (most cited first, 2 of 2)

- [Planning as Descent: Goal-Conditioned Latent Trajectory Synthesis in Learned Energy Landscapes](https://mlsanity.com/paper/2512.17846/) (2025)
- [Recovering Hidden Reward in Diffusion-Based Policies](https://mlsanity.com/paper/2605.00623/) (2026)

## Abstract (arXiv)

Implicit policies parameterized by generative models, such as Diffusion Policy, have become the standard for policy learning and Vision-Language-Action (VLA) models in robotics. However, these approaches often suffer from high computational cost, exposure bias, and unstable inference dynamics, which lead to divergence under distribution shifts. Energy-Based Models (EBMs) address these issues by learning energy landscapes end-to-end and modeling equilibrium dynamics, offering improved robustness and reduced exposure bias. Yet, policies parameterized by EBMs have historically struggled to scale effectively. Recent work on Energy-Based Transformers (EBTs) demonstrates the scalability of EBMs to high-dimensional spaces, but their potential for solving core challenges in physically embodied models remains underexplored. We introduce a new energy-based architecture, EBT-Policy, that solves core issues in robotic and real-world settings. Across simulated and real-world tasks, EBT-Policy consistently outperforms diffusion-based policies, while requiring less training and inference computation. Remarkably, on some tasks it converges within just two inference steps, a 50x reduction compared to Diffusion Policy's 100. Moreover, EBT-Policy exhibits emergent capabilities not seen in prior models, such as zero-shot recovery from failed action sequences using only behavior cloning and without explicit retry training. By leveraging its scalar energy for uncertainty-aware inference and dynamic compute allocation, EBT-Policy offers a promising path toward robust, generalizable robot behavior under distribution shifts.