MARAG-R1：通过强化学习驱动的多工具智能体检索超越单一检索器
MARAG-R1: Beyond Single Retriever via Reinforcement-Learned Multi-Tool Agentic Retrieval
AI总结：
针对单一检索器限制RAG信息获取的问题，提出强化学习驱动的多工具智能体检索框架MARAG-R1，通过动态协调四种检索工具并交错推理与检索，在语料库级推理任务上取得最先进结果。
摘要：
大型语言模型（LLMs）擅长推理与生成，但本质上受限于静态预训练数据，导致事实不准确且对新信息适应性弱。检索增强生成（RAG）通过将LLMs基于外部知识来解决这个问题；然而，RAG的有效性关键取决于模型是否能充分获取相关信息。现有RAG系统依赖单一检索器进行固定的top-k选择，限制了对语料库狭窄且静态子集的访问。因此，这种单检索器范式已成为全面获取外部信息的主要瓶颈，尤其是在需要语料库级推理的任务中。为克服此局限，我们提出了MARAG-R1，这是一个强化学习的多工具RAG框架，使LLMs能够动态协调多种检索机制，以更广泛、更精确地获取信息。MARAG-R1为模型配备了四种检索工具——语义搜索、关键词搜索、过滤和聚合——并通过两阶段训练过程学习如何以及何时使用它们：监督微调随后进行强化学习。这种设计允许模型交错推理和检索，逐步为语料库级合成收集足够证据。在GlobalQA、HotpotQA和2WikiMultiHopQA上的实验表明，MARAG-R1大幅超越强基线，并在语料库级推理任务中取得新的最先进结果。
英文摘要：
Large Language Models (LLMs) excel at reasoning and generation but are inherently limited by static pretraining data, resulting in factual inaccuracies and weak adaptability to new information. Retrieval-Augmented Generation (RAG) addresses this issue by grounding LLMs in external knowledge; However, the effectiveness of RAG critically depends on whether the model can adequately access relevant information. Existing RAG systems rely on a single retriever with fixed top-k selection, restricting access to a narrow and static subset of the corpus. As a result, this single-retriever paradigm has become the primary bottleneck for comprehensive external information acquisition, especially in tasks requiring corpus-level reasoning. To overcome this limitation, we propose MARAG-R1, a reinforcement-learned multi-tool RAG framework that enables LLMs to dynamically coordinate multiple retrieval mechanisms for broader and more precise information access. MARAG-R1 equips the model with four retrieval tools -- semantic search, keyword search, filtering, and aggregation -- and learns both how and when to use them through a two-stage training process: supervised fine-tuning followed by reinforcement learning. This design allows the model to interleave reasoning and retrieval, progressively gathering sufficient evidence for corpus-level synthesis. Experiments on GlobalQA, HotpotQA, and 2WikiMultiHopQA demonstrate that MARAG-R1 substantially outperforms strong baselines and achieves new state-of-the-art results in corpus-level reasoning tasks.
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。
