arXiv cs.CL· Xinze Li, Dingwen Zhang, Zhenghao Liu, Yukun Yan, Shuo Wang, Yu Gu, Ge Yu, Maosong Sun·· 13 小时前AI 评分31
MAPS：用宏自适应并行推理调控 RAG 中的搜索动量
MAPS: Macro-Adaptive Parallel Reasoning for Regulating Search Momentum in Retrieval-Augmented Generation
AI 导读
MAPS 是一个宏自适应并行推理框架，通过保留检索知识与精炼推理状态、并将顺序推理扩展为并行推理，来调控搜索动量、缓解查询意图漂移。该框架在每次迭代中识别互补检索方向、并行生成子查询并整合证据更新知识状态。在六个问答基准上，MAPS 在不同骨干模型下均优于代表性 RAG 方法，代码与资源已公开。
正文 · 原文
Abstract:Retrieval-Augmented Generation (RAG) improves the performance of Large Language Models (LLMs) by retrieving external knowledge. Recently, some RAG methods interleave reasoning and retrieval, enabling LLMs to progressively generate sub-queries and retrieve external knowledge. However, these methods may suffer from redundant or ineffective sub-queries and insufficiently diverse query exploration. Moreover, due to the tightly interleaved nature of reasoning and retrieval, it remains unclear how the evolving reasoning process influences query intent. To characterize the evolution of query intent during reasoning, we introduce search momentum, which captures the accumulated retrieval tendency induced by historical changes in generated sub-queries along the reasoning trajectory. Through momentum-based analysis, we find that the query generation process tends to continuously evolve along existing retrieval trajectories. Based on this observation, we propose MAPS, a Macro-Adaptive Parallel Reasoning framework for regulating search momentum and mitigating query-intent drift. MAPS first retains the retrieved knowledge and a refined reasoning state, thereby reducing the influence of historical reasoning trajectories on subsequent sub-query generation. Subsequently, MAPS extends the conventional sequential reasoning process into a parallel reasoning paradigm. At each iteration, MAPS identifies complementary retrieval directions, generates corresponding sub-queries for parallel retrieval, and consolidates the retrieved evidence to update the knowledge and reasoning states. Experiments on six question-answering benchmarks demonstrate that MAPS consistently outperforms representative RAG methods across different backbone models. All code and resources are available at this https URL.
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.29792 [cs.CL] |
| (or arXiv:2610.29792v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.29792 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Xinze Li [view email]
[v1]
Wed, 21 Oct 2026 14:19:17 UTC (941 KB)
来源：arXiv cs.CL · arxiv.org