开放深度搜索：通过开源推理代理实现搜索民主化

Open Deep Search: Democratizing Search with Open-source Reasoning Agents

March 26, 2025

作者: Salaheddin Alzubi, Creston Brooks, Purva Chiniya, Edoardo Contente, Chiara von Gerlach, Lucas Irwin, Yihan Jiang, Arda Kaz, Windsor Nguyen, Sewoong Oh, Himanshu Tyagi, Pramod Viswanath

cs.AI

摘要

我们推出开放深度搜索（Open Deep Search, ODS），旨在弥合专有搜索AI解决方案（如Perplexity的Sonar Reasoning Pro和OpenAI的GPT-4o Search Preview）与其开源替代品之间日益扩大的差距。ODS的主要创新在于，通过引入能够明智运用网络搜索工具来解答查询的推理代理，增强了最新开源大语言模型（LLMs）的推理能力。具体而言，ODS包含两个与用户选定的基础LLM协同工作的组件：开放搜索工具和开放推理代理。开放推理代理负责解读给定任务，并通过编排一系列动作（包括调用工具，其中之一便是开放搜索工具）来完成它。开放搜索工具是一种新型网络搜索工具，其性能超越专有同类产品。结合强大的开源推理LLMs，如DeepSeek-R1，ODS在SimpleQA和FRAMES两个基准测试上几乎达到并有时超越现有最先进基线。例如，在FRAMES评估基准上，ODS将最新发布的GPT-4o Search Preview的最佳基线准确率提升了9.7%。ODS是一个通用框架，能够无缝增强任何LLMs——例如，在SimpleQA上取得82.4%、在FRAMES上取得30.1%的DeepSeek-R1——通过赋予其搜索与推理能力，实现最先进性能：在SimpleQA上达到88.3%，在FRAMES上达到75.3%。

English

We introduce Open Deep Search (ODS) to close the increasing gap between the proprietary search AI solutions, such as Perplexity's Sonar Reasoning Pro and OpenAI's GPT-4o Search Preview, and their open-source counterparts. The main innovation introduced in ODS is to augment the reasoning capabilities of the latest open-source LLMs with reasoning agents that can judiciously use web search tools to answer queries. Concretely, ODS consists of two components that work with a base LLM chosen by the user: Open Search Tool and Open Reasoning Agent. Open Reasoning Agent interprets the given task and completes it by orchestrating a sequence of actions that includes calling tools, one of which is the Open Search Tool. Open Search Tool is a novel web search tool that outperforms proprietary counterparts. Together with powerful open-source reasoning LLMs, such as DeepSeek-R1, ODS nearly matches and sometimes surpasses the existing state-of-the-art baselines on two benchmarks: SimpleQA and FRAMES. For example, on the FRAMES evaluation benchmark, ODS improves the best existing baseline of the recently released GPT-4o Search Preview by 9.7% in accuracy. ODS is a general framework for seamlessly augmenting any LLMs -- for example, DeepSeek-R1 that achieves 82.4% on SimpleQA and 30.1% on FRAMES -- with search and reasoning capabilities to achieve state-of-the-art performance: 88.3% on SimpleQA and 75.3% on FRAMES.