{"ID":2899575,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.00606","arxiv_id":"2507.00606","title":"Mixture of Reasonings: Teach Large Language Models to Reason with Adaptive Strategies","abstract":"Large language models (LLMs) excel in complex tasks through advanced prompting techniques like Chain-of-Thought (CoT) and Tree-of-Thought (ToT), but their reliance on manually crafted, task-specific prompts limits adaptability and efficiency. We introduce Mixture of Reasoning (MoR), a training framework that embeds diverse reasoning strategies into LLMs for autonomous, task-adaptive reasoning without external prompt engineering. MoR has two phases: Thought Generation, creating reasoning chain templates with models like GPT-4o, and SFT Dataset Construction, pairing templates with benchmark datasets for supervised fine-tuning. Our experiments show that MoR significantly enhances performance, with MoR150 achieving 0.730 (2.2% improvement) using CoT prompting and 0.734 (13.5% improvement) compared to baselines. MoR eliminates the need for task-specific prompts, offering a generalizable solution for robust reasoning across diverse tasks.","short_abstract":"Large language models (LLMs) excel in complex tasks through advanced prompting techniques like Chain-of-Thought (CoT) and Tree-of-Thought (ToT), but their reliance on manually crafted, task-specific prompts limits adaptability and efficiency. We introduce Mixture of Reasoning (MoR), a training framework that embeds div...","url_abs":"https://arxiv.org/abs/2507.00606","url_pdf":"https://arxiv.org/pdf/2507.00606v2","authors":"[\"Tao Xiong\",\"Xavier Hu\",\"Wenyan Fan\",\"Shengyu Zhang\"]","published":"2025-07-01T09:39:04Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}