O-Researcher: 通过多智能体蒸馏和智能体强化学习构建开放式深度研究模型
O-Researcher: An Open Ended Deep Research Model via Multi-Agent Distillation and Agentic RL
AI总结：
O-Researcher通过多智能体蒸馏和智能体强化学习，构建开放式深度研究模型，实现开源模型在多个基准上的性能提升。
摘要：
封闭源和开源大型语言模型（LLMs）之间性能差距主要归因于高质量训练数据获取上的差异。为弥合这一差距，我们引入了一种自动化合成复杂、研究级教学数据的新型框架。我们的方法聚焦于一个多智能体工作流程，其中协作的AI代理模拟复杂的工具集成推理以生成多样且高保真的数据。利用此合成数据，我们开发了两阶段训练策略，结合监督微调与一种新的强化学习方法，旨在最大化模型对齐和能力。广泛实验表明，我们的框架使开源模型在多个规模上得以提升，使其在主要深度研究基准上达到新的最先进的性能。本工作提供了一条可扩展且有效的途径，以推动开源LLMs的发展，而无需依赖专有数据或模型。
英文摘要：
The performance gap between closed-source and open-source large language models (LLMs) is largely attributed to disparities in access to high-quality training data. To bridge this gap, we introduce a novel framework for the automated synthesis of sophisticated, research-grade instructional data. Our approach centers on a multi-agent workflow where collaborative AI agents simulate complex tool-integrated reasoning to generate diverse and high-fidelity data end-to-end. Leveraging this synthesized data, we develop a two-stage training strategy that integrates supervised fine-tuning with a novel reinforcement learning method, designed to maximize model alignment and capability. Extensive experiments demonstrate that our framework empowers open-source models across multiple scales, enabling them to achieve new state-of-the-art performance on the major deep research benchmark. This work provides a scalable and effective pathway for advancing open-source LLMs without relying on proprietary data or models.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
