{"slug": "recursive-think-answer-process-for-llms-and-vlms", "title": "Recursive Think-Answer Process for LLMs and VLMs", "summary": "Researchers propose Recursive Think-Answer Process (R-TAP), a method enabling large language models (LLMs) and vision-language models (VLMs) to iteratively refine their answers, outperforming single-pass approaches. R-TAP uses a confidence generator and two complementary rewards—Recursively Confidence Increase Reward and Final Answer Confidence Reward—to improve accuracy and reduce self-reflective errors like 'Oops!' in models such as DeepSeek-R1.", "body_md": "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.", "url": "https://wpnews.pro/news/recursive-think-answer-process-for-llms-and-vlms", "canonical_source": "https://research.nvidia.com/publication/2026-06_recursive-think-answer-process-llms-and-vlms", "published_at": "2026-08-11 06:55:06+00:00", "updated_at": "2026-08-11 07:09:02.952642+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning", "large-language-models", "ai-research"], "entities": ["DeepSeek-R1", "R-TAP"], "alternates": {"html": "https://wpnews.pro/news/recursive-think-answer-process-for-llms-and-vlms", "markdown": "https://wpnews.pro/news/recursive-think-answer-process-for-llms-and-vlms.md", "text": "https://wpnews.pro/news/recursive-think-answer-process-for-llms-and-vlms.txt", "jsonld": "https://wpnews.pro/news/recursive-think-answer-process-for-llms-and-vlms.jsonld"}}