ManuSearch: Democratizing Deep Search in Large Language Models with a Transparent and Open Multi-Agent Framework

TL;DR

ManuSearch is a transparent, multi-agent framework that enhances deep web search and reasoning capabilities of large language models, promoting open and reproducible research in this domain.

Contribution

It introduces a modular multi-agent system for deep web search and reasoning, along with a new benchmark for evaluating open-web reasoning in LLMs.

Findings

Outperforms prior open-source baselines

Surpasses leading closed-source systems

Enables reproducible and extensible deep search research

Abstract

Recent advances in web-augmented large language models (LLMs) have exhibited strong performance in complex reasoning tasks, yet these capabilities are mostly locked in proprietary systems with opaque architectures. In this work, we propose \textbf{ManuSearch}, a transparent and modular multi-agent framework designed to democratize deep search for LLMs. ManuSearch decomposes the search and reasoning process into three collaborative agents: (1) a solution planning agent that iteratively formulates sub-queries, (2) an Internet search agent that retrieves relevant documents via real-time web search, and (3) a structured webpage reading agent that extracts key evidence from raw web content. To rigorously evaluate deep reasoning abilities, we introduce \textbf{ORION}, a challenging benchmark focused on open-web reasoning over long-tail entities, covering both English and Chinese. Experimental results show that ManuSearch substantially outperforms prior open-source baselines and even surpasses leading closed-source systems. Our work paves the way for reproducible, extensible research in open deep search systems. We release the data and code in https://github.com/RUCAIBox/ManuSearch