RAG-R1: Incentivizing the Search and Reasoning Capabilities of LLMs through Multi-query Parallelism
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914249763192832 |
|---|---|
| author | Tan, Zhiwen Huang, Jiaming Wu, Qintong Zhang, Hongxuan Zhuang, Chenyi Gu, Jinjie |
| author_facet | Tan, Zhiwen Huang, Jiaming Wu, Qintong Zhang, Hongxuan Zhuang, Chenyi Gu, Jinjie |
| contents | Large Language Models (LLMs), despite their remarkable capabilities, are prone to generating hallucinated or outdated content due to their static internal knowledge. While Retrieval-Augmented Generation (RAG) integrated with Reinforcement Learning (RL) offers a solution, these methods are fundamentally constrained by a single-query mode, leading to prohibitive latency and inherent brittleness. To overcome these limitations, we introduce RAG-R1, a novel two-stage training framework centered around multi-query parallelism. Our framework enables LLMs to adaptively leverage internal and external knowledge during the reasoning process while transitioning from the single-query mode to multi-query parallelism. This architectural shift bolsters reasoning robustness while significantly reducing inference latency. Extensive experiments on seven question-answering benchmarks confirm the superiority of our method, which outperforms the strongest baseline by up to 13.7% and decreases inference time by 11.1%. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_02962 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | RAG-R1: Incentivizing the Search and Reasoning Capabilities of LLMs through Multi-query Parallelism Tan, Zhiwen Huang, Jiaming Wu, Qintong Zhang, Hongxuan Zhuang, Chenyi Gu, Jinjie Computation and Language Artificial Intelligence Information Retrieval Large Language Models (LLMs), despite their remarkable capabilities, are prone to generating hallucinated or outdated content due to their static internal knowledge. While Retrieval-Augmented Generation (RAG) integrated with Reinforcement Learning (RL) offers a solution, these methods are fundamentally constrained by a single-query mode, leading to prohibitive latency and inherent brittleness. To overcome these limitations, we introduce RAG-R1, a novel two-stage training framework centered around multi-query parallelism. Our framework enables LLMs to adaptively leverage internal and external knowledge during the reasoning process while transitioning from the single-query mode to multi-query parallelism. This architectural shift bolsters reasoning robustness while significantly reducing inference latency. Extensive experiments on seven question-answering benchmarks confirm the superiority of our method, which outperforms the strongest baseline by up to 13.7% and decreases inference time by 11.1%. |
| title | RAG-R1: Incentivizing the Search and Reasoning Capabilities of LLMs through Multi-query Parallelism |
| topic | Computation and Language Artificial Intelligence Information Retrieval |
| url | https://arxiv.org/abs/2507.02962 |