1. [Publications](/publications)
2. Recursive Think-Answer Process for LLMs and VLMs

 # Recursive Think-Answer Process for LLMs and VLMs

  ![Publication image](/sites/default/files/styles/wide/public/default_images/default.jpeg?itok=TfIobf92 "Publication image")

 Think-Answer reasoners such as DeepSeek-R1 have made notable progress by leveraging interpretable internal reasoning. However, despite the frequent presence of self-reflective cues like "Oops!", they remain vulnerable to output errors during single-pass inference. To address this limitation, we propose an efficient Recursive Think-Answer Process (R-TAP) that enables models to engage in iterative reasoning cycles and generate more accurate answers, going beyond conventional single-pass approaches. Central to this approach is a confidence generator that evaluates the certainty of model responses and guides subsequent improvements. By incorporating two complementary rewards-Recursively Confidence Increase Reward and Final Answer Confidence Reward-we show that R-TAP-enhanced models consistently outperform conventional single-pass methods for both large language models (LLMs) and vision-language models (VLMs). Moreover, by analyzing the frequency of "Oops"-like expressions in model responses, we find that R-TAP-applied models exhibit significantly fewer self-reflective patterns, resulting in more stable and faster inference-time reasoning. We hope R-TAP pave the way evolving into efficient and elaborated methods to refine the reasoning processes of future AI.

 ## Authors

[Byung-Kwan Lee](/person/byung-kwan-lee)

Youngchae Chee (KAIST)

Yong Man Ro (KAIST)

 ## Publication Date

Monday, June 1, 2026

 ## Published in

[CVPR 2026 Findings](https://arxiv.org/abs/2603.02099)

 ## Research Area

[Artificial Intelligence and Machine Learning ](/research-area/machine-learning-artificial-intelligence)

[Computer Vision](/research-area/computer-vision)

[Natural Language Processing](/research-area/natural-language-processing)