---
base_model:
- Qwen/Qwen3-8B-Base
datasets:
- Elliott/Openr1-Math-46k-8192
language:
- en
license: apache-2.0
metrics:
- accuracy
pipeline_tag: text-generation
library_name: transformers
---

[![arXiv](https://img.shields.io/badge/arXiv-2510.26109-b31b1b.svg?logo=arxiv)](https://arxiv.org/abs/2510.26109)
[![GitHub](https://img.shields.io/badge/GitHub-LTE-blue?logo=github)](https://github.com/JamyDon/LTE)
[![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg?logo=apache)](LICENSE)

## Introduction
LTE is an RLVR approach that mitigates the exploration stagnation of LMs by their previously self-made mistakes and does not require any external expert guidance. LTE improves the performance upper bound of LMs and enhances both exploitation and exploration during training.

## Key Highlights
- **Self-generated Hints**: LTE uses the errors generated by the LMs themselves during training as hints.
- **No External Expert Guidance**: LTE does not require any external expert guidance to mitigate the exploration stagnation of LMs.

## Inference
Here is an example of using LTE models for inference:

```python
from transformers import AutoTokenizer
from vllm import LLM, SamplingParams

model_path="JamyDohrn/LTE-Qwen3-8B-Base"

question = "which number is larger? 9.11 or 9.9?"

tokenizer = AutoTokenizer.from_pretrained(model_path)
messages = [{"role": "user", "content": question}]
chat = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)

llm = LLM(model=model_path)
params = SamplingParams(temperature=0.6, max_tokens=32768)
outputs = llm.generate([chat], params)
print(outputs[0].outputs[0].text)
```

## Acknowledgements
LTE is built on the following repositories and we thank their teams for their valuable contributions to the community:
- [verl](https://github.com/volcengine/verl)
- [LUFFY](https://github.com/ElliottYan/LUFFY)
- [LIMO](https://github.com/GAIR-NLP/LIMO)

## Citation
If you find our work useful, feel free to cite our paper:
```bib
@misc{tang2026steprivertwicelearning,
      title={Do Not Step Into the Same River Twice: Learning to Reason from Trial and Error}, 
      author={Chenming Tang and Hsiu-Yuan Huang and Weijie Liu and Clive Bai and Saiyong Yang and Yunfang Wu},
      year={2026},
      eprint={2510.26109},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/2510.26109}, 
}
```