64 lines
2.3 KiB
Markdown
64 lines
2.3 KiB
Markdown
---
|
||
license: apache-2.0
|
||
datasets:
|
||
- agentica-org/DeepScaleR-Preview-Dataset
|
||
base_model:
|
||
- deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
|
||
tags:
|
||
- reinforcement-learning
|
||
language:
|
||
- en
|
||
- zh
|
||
pipeline_tag: text-generation
|
||
library_name: transformers
|
||
---
|
||
|
||
<p align="center">
|
||
<img src="https://cdn-uploads.huggingface.co/production/uploads/64ed568ccf6118a9379a61b8/BHITqJU33sXqf-Jbytrxg.png" width="100"/>
|
||
<b><span style="font-size:28px">SIRI: Scaling Iterative Reinforcement Learning with Interleaved Compression</span></b>
|
||
</p>
|
||
|
||
|
||
|
||
<p align="center">
|
||
📃 <a href="https://arxiv.org" target="_blank">Paper</a> • 📝 <a href="https://arxiv.org" target="_blank">Wandb</a>
|
||
</p>
|
||
|
||
---
|
||
|
||
## 🔍 Overview
|
||
|
||
**SIRI (Scaling Iterative Reinforcement Learning with Interleaved Compression)** is a reinforcement-learning–based framework designed to improve the efficiency and accuracy of **Large Reasoning Models (LRMs)**.
|
||
|
||
Traditional RL training often causes **overthinking** and long, redundant reasoning traces. Prior methods that compress outputs (length penalties, pruning, or skipping thought tokens) improve efficiency but hurt accuracy.
|
||
|
||
SIRI solves this trade-off by **iteratively alternating between compression and expansion of the reasoning budget**, controlled by a cosine length scheduler. This approach dynamically balances concise reasoning with long-horizon exploration.
|
||
|
||
<p align="center">
|
||
<img src="https://cdn-uploads.huggingface.co/production/uploads/64ed568ccf6118a9379a61b8/SXow6xntEgrwhvWtzvrkE.png" alt="pareto_front" width="500"/>
|
||
</p>
|
||
|
||
---
|
||
|
||
## 🚀 Key Features
|
||
|
||
- **Interleaved Compression–Expansion**:
|
||
- *Compression phase*: forces concise, high-density reasoning by limiting rollout length.
|
||
- *Expansion phase*: restores longer rollouts to encourage exploration and planning.
|
||
- **Token Efficiency without Accuracy Loss**: Unlike previous methods, SIRI improves accuracy *while reducing average token usage*.
|
||
- **Iterative RL Training**: Built on GRPO with modifications from DAPO (clip-high/low decoupling, KL removal).
|
||
- **Generalization Across Model Sizes**: Validated on both **1.5B** and **7B** models.
|
||
|
||
---
|
||
|
||
## 📊 Benchmarks
|
||
|
||
|
||
|
||
|
||
|
||
---
|
||
|
||
## 📝 Citation
|
||
|
||
```bibtex |