Newest papers

MAPS: Macro-Adaptive Parallel Reasoning for Regulating Search Momentum in Retrieval-Augmented Generation

Xinze Li, Dingwen Zhang, Zhenghao Liu, Yukun Yan, Shuo Wang, Yu Gu, Ge Yu, Maosong Sun · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.29792 · cited by 0 works (OpenAlex) · open-access PDF

Indonesian

RAG meningkatkan kinerja Model Bahasa Besar (LLM) dengan mengembalikan pengetahuan eksternal. Baru-baru ini, beberapa metode RAG memperbarui interleave pertanyaan dan retrieval, memungkinkan LLM untuk secara progresif menghasilkan sub-keinginan dan mengembalikan pengetahuan eksternal. Namun, metode ini mungkin menderita dari redundant atau tidak efektif sub-keinginan dan sub-keinginan eksplorasi yang tidak cukup beragam. Selain itu, karena sifat ketat interleaved dari alasan dan retrieval, tetap tidak jelas bagaimana proses argumen yang berkembang mempengaruhi pertanyaan tujuan. Untuk menggambarkan evolusi pertanyaan selama argumen, kami memperkenalkan momentum pencarian paralel, yang menangkap akumulasi retribusi alasan yang dihasilkan oleh perubahan pengetahuan yang dikonsolidasikan kembali dalam sub-keinginan yang tersedia di sepanjang trajektori argumen konsolidasi paradigma. Melalui analisis

Machine translation (Meta M2M100); the English original follows.

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 https://github.com/NEUIR/MAPS.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Process (computing), Case-based reasoning, Reasoning system, Opportunistic reasoning, Deductive reasoning

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange