Scaling Retrieval-Augmented Reasoning with Parallel Search and Explicit Merging

TL;DR

MultiSearch is a reinforcement learning framework that improves reasoning accuracy in large language models by using multi-query retrieval and explicit merging to enhance information coverage and signal-to-noise ratio.

Contribution

It introduces multi-query retrieval and explicit merging in a reinforcement learning framework to address limitations of single-query retrieval in reasoning tasks.

Findings

MultiSearch outperforms baseline methods on seven benchmarks.

It enhances retrieval signal-to-noise ratio and reasoning accuracy.

Parallel retrieval and merging improve information coverage.

Abstract

Deep search agents have proven effective in enhancing LLMs by retrieving external knowledge during multi-step reasoning. However, existing methods often generate a single query for retrieval at each reasoning step, limiting information coverage and introducing high noise. This may result in low signal-to-noise ratios (SNR) during search, degrading reasoning accuracy and leading to unnecessary reasoning steps. In this paper, we introduce MultiSearch, an RL-based framework that addresses these limitations through multi-query retrieval and explicit merging of retrieved information. At each reasoning step, MultiSearch generates queries from multiple perspectives and retrieves external information in parallel, expanding the scope of relevant information and mitigating the reliance on any single retrieval result. Then, the agent consolidates and refines retrieved information at the merging process, improving the SNR and ensuring more accurate reasoning. Additionally, we propose a reinforcement learning framework with a multi-process reward design to optimize agents for both multi-query retrieval and information consolidation. Extensive experiments on seven benchmarks demonstrate that MultiSearch outperforms baseline methods, enhancing the SNR of retrieval and improving reasoning performance in question-answering tasks.