---
license: mit
library_name: transformers
tags:
- robotics
- reward-model
- video-language-model
- reasoning
- reinforcement-learning
- qwen3-vl
- bf16
pipeline_tag: image-text-to-text
datasets:
- Philip-MIT/sole_training_data
---

# SOLE-R1-8B

SOLE-R1-8B is a video-language reward reasoning model for robotics. It is designed to estimate task progress from robot video frames and a natural-language task description, producing both per-timestep reasoning traces and scalar progress predictions that can be used as rewards for online robot reinforcement learning.

This model accompanies the paper **“SOLE-R1: Video-Language Reasoning as the Sole Reward for On-Robot RL”** by Philip Schroeder, Thomas Weng, Karl Schmeckpeper, Eric Rosen, Stephen Hart, and Ondrej Biza.

- Paper: https://arxiv.org/abs/2603.28730
- Project page: https://philip-mit.github.io/sole-r1/
- Code: https://github.com/Philip-MIT/sole-r1-model
- Training data: https://huggingface.co/datasets/Philip-MIT/sole_training_data

## Model Description

SOLE-R1 predicts robot task progress from visual observations. Given an image or video-frame montage containing the first, previous, and current timestep views, plus a task description and prior progress value, the model outputs a reasoning trace and a scalar progress estimate.

Expected output format:

<think>reasoning about task progress</think><answer>progress%</answer>

The progress estimate is intended to serve as a dense reward signal for robotic reinforcement learning, especially when manually engineered rewards are unavailable.

## Intended Use

SOLE-R1-8B is intended for:

- Robotics reward prediction
- Online robot RL reward generation
- Evaluating task progress from robot videos
- Interpretable video-language reasoning for manipulation tasks
- Research on learned reward models and robotic foundation models

It is not intended as a general-purpose safety-critical robotics controller. The model should be validated in the target environment before use in closed-loop robotic systems.

## Quick Start

The recommended interface for inference is [RoboReason](https://github.com/Philip-MIT/roboreason):

# pip install -U roboreason

import roboreason as rr

video_paths = [
"test_videos/robosuite/lift/unsuccessful/robosuite_lift_episode_12_unsuccessful_max_reward_38.mp4"
]

task_description = "Pick up the cube from the table."

rewards, reasoning_traces = rr.generate(
model="SOLE-R1",
task_description=task_description,
video_paths=video_paths,
view_type_per_video=["external and wrist"],
verbose=False,
)

print(rewards)
print(reasoning_traces)



Optional pre-download:

from roboreason.utils.model_utils import get_model_dir

get_model_dir("sole-r1")

## Input Format

The model is trained to reason over robot task progress using prompts that include:

- A robot task description
- The first timestep progress, typically `0%`
- The previous timestep progress
- Visual observations from the first, previous, and current timesteps
- Multiple camera views when available, such as external and wrist cameras

Example task description:

Pick up the cube from the table.

## Output Format

The expected output format is:

<think>[reasoning about visual task progress]</think><answer>[current task progress]%</answer>

Example:

<think>The gripper has moved closer to the cube but has not yet grasped or lifted it. This indicates incremental progress from the previous timestep.</think><answer>22%</answer>

Downstream systems should parse the numeric value inside `<answer>...</answer>` as the reward/progress estimate.

## Training Data

The model was trained on the [SOLE-R1-8B](https://huggingface.co/Philip-MIT/SOLE-R1-8B) training dataset.

The dataset contains robot task progress examples with images, prompts, reasoning completions, and progress labels. The full dataset is approximately 2TB.

Streaming example:

from datasets import load_dataset

ds = load_dataset(
"Philip-MIT/sole_training_data",
split="train",
streaming=True,
)

for row in ds:
print(row)
break

## Citation

BibTeX:

@misc {schroeder2026soler1,
title={SOLE-R1: Video-Language Reasoning as the Sole Reward for On-Robot RL},
author={Philip Schroeder and Thomas Weng and Karl Schmeckpeper and Eric Rosen and Stephen Hart and Ondrej Biza},
year={2026},
eprint={2603.28730},
archivePrefix={arXiv},
primaryClass={cs.RO}
}

## License

This repository is released under the MIT License.