CWM：用于自适应检索增强生成与推理能力的可控白盒元提示
CWM: Controllable White-Box Meta-Prompting for Adaptive Retrieval-Augmented Generation and Reasoning Ability
- Hanyang University（汉阳大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出统一框架及可控白盒元提示（CWM），低成本实现自适应RAG，无需外部模块或多采样，在多个基准上达到最优，并支持推理任务，通过内部信号调节检索决策。
AI中文摘要：
近年来，大型语言模型（LLMs）因其强大的语言理解和生成能力而受到广泛关注，展现出令人印象深刻的推理能力以及对外部知识的有效利用。许多研究提出了专门针对单个任务性能提升的方法。然而，具有讽刺意味的是，只有少数尝试探索了通用、任务无关的方法。在这项工作中，我们提出了一个统一框架，整合了推理和检索增强生成（RAG）任务。我们进一步提出了可控白盒元提示（CWM），一种低成本的白盒方法，用于此前由黑盒方法主导的自适应RAG任务，无需外部决策模块或多重采样。CWM在三个自适应RAG基准上，在包括GPT-oss-20b、Qwen3-14b和Llama3.1-8b在内的最新LLMs上取得了最先进的性能，同时通过扩展到推理任务展示了强大的通用性。此外，CWM通过操纵内部模型信号来调节检索决策，提供了可控性。我们的代码可在以下网址获取：https://this.url。
英文摘要：
Recently, Large Language Models (LLMs) have gained significant attention due to their strong language understanding and generation capabilities, demonstrating impressive reasoning abilities as well as effective utilization of external knowledge. Many studies have proposed methods that specialize in improving performance for individual tasks. However, ironically, only a limited number of attempts have explored general-purpose, task-agnostic methods. In this work, we present a unified framework integrating reasoning and Retrieval-Augmented Generation (RAG) tasks. We further propose Controllable White-Box Meta-Prompting (CWM), a low-cost white-box method for adaptive RAG tasks previously dominated by black-box approaches, without requiring external decision modules or multi-sampling. CWM achieves state-of-the-art performance on three adaptive RAG benchmarks across recent LLMs, including GPT-oss-20b, Qwen3-14b, and Llama3.1-8b, while also demonstrating strong generality by extending to reasoning tasks. In addition, CWM provides controllability by enabling retrieval decisions to be regulated through the manipulation of internal model signals. Our code is available at https://github.com/JeongEunhye00/CWM.
