app.py

import gradio as gr


with gr.Blocks(css="""
#my-img img {
    width: 50% !important;
    display: block;
    margin-left: auto;
    margin-right: auto;
}
""") as demo:
    gr.HTML("""
<div align="center">

<h1>Elastic Reasoning
<div>
<div>
<h3>🚀 Scalable Chain of Thoughts via Elastic Reasoning 🌟
</div>
</div>
<br>
</div>
    """)
    gr.Markdown(
    """
[![Paper](https://img.shields.io/badge/paper-A42C25?style=for-the-badge&logo=arxiv&logoColor=white)](https://arxiv.org/pdf/2505.05315)
[![Hugging Face Collection](https://img.shields.io/badge/E1-fcd022?style=for-the-badge&logo=huggingface&logoColor=000&labelColor)](https://huggingface.co/collections/Salesforce/elastic-reasoning-682b4bba108d6ea0a8bab275)
[![Github](https://img.shields.io/badge/Elastic_Reasoning-000000?style=for-the-badge&logo=github&logoColor=000&logoColor=white)](https://github.com/SalesforceAIResearch/Elastic-Reasoning)

## Table of Contents
- [Introduction](#introduction)
- [Environment Setup](#environment-setup)
- [Training](#training)
- [Evaluation](#evaluation)

## Introduction
We propose **Elastic Reasoning**, a novel framework for scalable chain of thoughts
that explicitly separates reasoning into two phases—`thinking and solution`—with
independently allocated budgets. At test time, Elastic Reasoning prioritize that
completeness of solution segments, significantly improving reliability under tight
resource constraints. To train models that are robust to truncated thinking, we
introduce a lightweight `budget-constrained rollout` strategy, integrated into GRPO,
which teaches the model to reason adaptively when the thinking process is cut
short and generalizes effectively to unseen budget constraints without additional
training.
    """)
    gr.Image("figs/framework.png", label="Framework", show_label=False, elem_id="my-img")

    gr.Markdown(
    """
**Main Takeaways**
1. ✂️ Thinking + Solution are explicitly separated with independent budgets — boosting reliability under tight compute constraints.
2. 🧠 Budget-Constrained Rollout: We train models to handle truncated reasoning using GRPO.
3. 📈 Flexible scalability: Robust performance across diverse inference budgets on reasoning benchmarks like AIME and LiveCodeBench.
4. ⚙️ Better performance with fewer tokens: Our trained model generates outputs that are 30% shorter while maintaining (or even improving) accuracy.
    """)
    gr.HTML("""
<p align="center">
  <img src="figs/aime.png" width="46%" />
    <img src="figs/livecode.png" width="48%" />
</p>

<p align="center">
  <img src="figs/codetable.png" width="90%" />
</p>
    """)
    gr.Markdown(
    """
## Citation


```bibtex
@article{xu2025scalable,
  title={Scalable Chain of Thoughts via Elastic Reasoning},
  author={Xu, Yuhui and Dong, Hanze and Wang, Lei and Sahoo, Doyen and Li, Junnan and Xiong, Caiming},
  journal={arXiv preprint arXiv:2505.05315},
  year={2025}
}
```
    """)


if __name__ == "__main__":
    demo.launch()