base_model, datasets, language, license, metrics, pipeline_tag, library_name

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

LTE-Qwen3-8B-Base

Introduction

LTE (Learning to reason from Trial and Error) is an RLVR (Reinforcement Learning with Verifiable Rewards) approach presented in the paper Do Not Step Into the Same River Twice: Learning to Reason from Trial and Error.

LTE mitigates the exploration stagnation of Language Models (LMs) by utilizing their previously self-made mistakes as hints, requiring no external expert guidance. It 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:

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
• LUFFY
• LIMO

Citation

If you find our work useful, feel free to cite our paper:

@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}, 
}