RuleReasoner: Reinforced Rule-based Reasoning via Domain-aware Dynamic Sampling
Paper • 2506.08672 • Published • 30
Question Answering
Transformers
Safetensors
English
qwen3
text-generation
rule-based reasoning
text-generation-inference
# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("RuleReasoner/RuleReasoner-8B")
model = AutoModelForCausalLM.from_pretrained("RuleReasoner/RuleReasoner-8B", device_map="auto")Quick Links
Citation
If you use the model in your research, please cite the original papers as below.
@article{liu2025rulereasoner,
title={RuleReasoner: Reinforced Rule-based Reasoning via Domain-aware Dynamic Sampling},
author={Yang Liu and Jiaqi Li and Zilong Zheng},
year={2025},
eprint={2506.08672},
archivePrefix={arXiv},
primaryClass={cs.CL},
url={https://arxiv.org/abs/2506.08672},
}
- Downloads last month
- 27
# Use a pipeline as a high-level helper # Warning: Pipeline type "question-answering" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("question-answering", model="RuleReasoner/RuleReasoner-8B")