开源推理代理让普通模型也能实现顶级搜索能力
Open Deep Search: Democratizing Search with Open-source Reasoning Agents
- 用开源推理代理协调搜索工具,提升大模型的问答能力
- 在FRAMES上比GPT-4o搜索预览高9.7%准确率,简单问答达88.3%
- 适配DeepSeek-R1等开源模型,可复现顶尖搜索性能
我们提出Open Deep Search(ODS),弥合专有搜索AI(如Perplexity Sonar Reasoning Pro和OpenAI GPT-4o Search Preview)与开源方案之间的差距。核心创新是通过推理代理,使最新开源大模型能智能调用网络搜索工具以回答复杂问题。ODS包含两个组件:开放搜索工具(Open Search Tool)和开放推理代理(Open Reasoning Agent)。后者解析任务并编排一系列操作,包括调用搜索工具。该搜索工具表现优于专有方案。结合DeepSeek-R1等强大开源推理模型,ODS在SimpleQA和FRAMES两个基准上接近甚至超越现有最优水平。例如,在FRAMES上,相比最新发布的GPT-4o Search Preview基线,准确率提升9.7%。作为通用框架,它可无缝增强任意大模型——如在SimpleQA上达82.4%、FRAMES上达30.1%的DeepSeek-R1——使其性能提升至SimpleQA 88.3%、FRAMES 75.3%。
原文摘要 · Abstract (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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。