{"ID":2856731,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.10528","arxiv_id":"2510.10528","title":"Merlin's Whisper: Enabling Efficient Reasoning in Large Language Models via Black-box Persuasive Prompting","abstract":"Large reasoning models (LRMs) have demonstrated remarkable proficiency in tackling complex tasks through step-by-step thinking. However, this lengthy reasoning process incurs substantial computational and latency overheads, hindering the practical deployment of LRMs. This work presents a new approach to mitigating overthinking in LRMs via black-box persuasive prompting. By treating LRMs as black-box communicators, we investigate how to persuade them to generate concise responses without compromising accuracy. We introduce Whisper, an iterative refinement framework that generates high-quality persuasive prompts from diverse perspectives. Experiments across multiple benchmarks demonstrate that Whisper consistently reduces token usage while preserving performance. Notably, Whisper achieves a 3x reduction in average response length on simple GSM8K questions for the Qwen3 model series and delivers an average ~40% token reduction across all benchmarks. For closed-source APIs, Whisper reduces token usage on MATH-500 by 46% for Claude-3.7 and 50% for Gemini-2.5. Further analysis reveals the broad applicability of Whisper across data domains, model scales, and families, underscoring the potential of black-box persuasive prompting as a practical strategy for enhancing LRM efficiency.","short_abstract":"Large reasoning models (LRMs) have demonstrated remarkable proficiency in tackling complex tasks through step-by-step thinking. However, this lengthy reasoning process incurs substantial computational and latency overheads, hindering the practical deployment of LRMs. This work presents a new approach to mitigating over...","url_abs":"https://arxiv.org/abs/2510.10528","url_pdf":"https://arxiv.org/pdf/2510.10528v3","authors":"[\"Heming Xia\",\"Cunxiao Du\",\"Rui Li\",\"Chak Tou Leong\",\"Yongqi Li\",\"Wenjie Li\"]","published":"2025-10-12T09:56:47Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.LG\"]","methods":"[\"Language Model\"]","has_code":false}