重试就足够了吗？无需语言化反馈增强大语言模型推理能力
Are Retrials All You Need? Enhancing Large Language Model Reasoning Without Verbalized Feedback
AI总结：
针对大型语言模型推理中复杂迭代策略成本高的问题，提出无需反馈的重试机制，让模型识别错误后重新尝试，该简单方法常优于复杂框架，为高效推理提供新方向。
摘要：
大型语言模型（LLMs）的最新进展推动了通用自主智能体的发展，在不同领域的复杂推理任务中展现出卓越性能。这一热潮催生了大量基于提示的推理框架。近期研究聚焦于通过自我评估和语言化反馈优化输出的迭代推理策略。然而，这些策略需要额外计算复杂度让模型识别并纠正错误，导致成本显著增加。本研究提出“无反馈重试”概念，这是一种极其简单却强大的机制：LLMs识别错误答案后重新尝试解决问题，以此增强推理框架。与传统迭代优化方法不同，该方法无需显式自我反思或语言化反馈，简化了优化过程。研究发现，更简单的基于重试的方法常优于更复杂的推理框架，表明复杂方法的收益未必能抵消其计算成本。通过挑战“更复杂的推理策略必然带来更好性能”这一普遍假设，本研究为更简单、高效的方法如何实现最优结果提供了新见解。那么，重试就足够了吗？
英文摘要：
Recent advancements in large language models (LLMs) have catalyzed the development of general-purpose autonomous agents, demonstrating remarkable performance in complex reasoning tasks across various domains. This surge has spurred the evolution of a plethora of prompt-based reasoning frameworks. A recent focus has been on iterative reasoning strategies that refine outputs through self-evaluation and verbalized feedback. However, these strategies require additional computational complexity to enable models to recognize and correct their mistakes, leading to a significant increase in their cost. In this work, we introduce the concept of ``retrials without feedback'', an embarrassingly simple yet powerful mechanism for enhancing reasoning frameworks by allowing LLMs to retry problem-solving attempts upon identifying incorrect answers. Unlike conventional iterative refinement methods, our method does not require explicit self-reflection or verbalized feedback, simplifying the refinement process. Our findings indicate that simpler retrial-based approaches often outperform more sophisticated reasoning frameworks, suggesting that the benefits of complex methods may not always justify their computational costs. By challenging the prevailing assumption that more intricate reasoning strategies inherently lead to better performance, our work offers new insights into how simpler, more efficient approaches can achieve optimal results. So, are retrials all you need?
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
