Deep Think with Confidence
Yichao Fu, Xuewei Wang, Hao Zhang, Yuandong Tian, Jiawei Zhao
Abstract
Large Language Models (LLMs) have shown great potential in reasoning tasks through test-time scaling methods like self-consistency with majority voting. However, this approach often leads to diminishing returns in accuracy and high computational overhead. To address these challenges, we introduce Deep Think with Confidence (DeepConf), a simple yet powerful method that enhances both reasoning efficiency and performance at test time. DeepConf leverages model-internal confidence signals to dynamically filter out low-quality reasoning traces during or after generation. It requires no additional model training or hyperparameter tuning and can be seamlessly integrated into existing serving frameworks. We evaluate DeepConf across a variety of tasks and the latest open-source models, including Qwen3 and GPT-OSS series. Notably, on challenging benchmarks such as AIME 2025, DeepConf@512 achieves up to 99.9\% accuracy and reduces generated tokens by up to 84.7\% compared to full parallel thinking. Anonymous code is available at https://anonymous.4open.science/r/deepconf-anonymous-E4E3
BibTeX
@inproceedings{
fu2026deep,
title={Deep Think with Confidence},
author={Yichao Fu and Xuewei Wang and Hao Zhang and Yuandong Tian and Jiawei Zhao},
booktitle={The Fourteenth International Conference on Learning Representations},
year={2026},
url={https://openreview.net/forum?id=8LqHs0KIM7}
}