用动态知识流驱动多智能体科研，提升复杂任务的推理与探索能力
FlowSearch: Advancing deep research with dynamic structured knowledge flow
- 构建可动态演化知识流的多智能体框架，实现任务分层与并行探索
- 在GAIA、HLE、GPQA等10个基准上表现优于主流方法，科学推理准确率最高达78.3%
- 适合需要跨领域深度推理的科研自动化场景，如论文分析与假设生成
深度研究是一项兼具广度与深度的复杂任务，需在多样知识空间中导航并处理多步依赖关系，这对智能体系统构成重大挑战。为此，我们提出FlowSearch——一种多智能体框架，通过主动构建和演化动态结构化知识流来驱动子任务执行与推理。该框架能够战略性地规划与扩展知识流，支持并行探索与层级任务分解，并根据中间推理结果与洞察实时调整知识流。FlowSearch在通用与科学基准（包括GAIA、HLE、GPQA和TRQA）上均达到竞争力表现，展现出在跨学科研究场景中的有效性及推动科学发现的潜力。代码已开源：https://github.com/InternScience/InternAgent。
原文摘要 · Abstract (English)
Deep research is an inherently challenging task that demands both breadth and depth of thinking. It involves navigating diverse knowledge spaces and reasoning over complex, multi-step dependencies, which presents substantial challenges for agentic systems. To address this, we propose FlowSearch, a multi-agent framework that actively constructs and evolves a dynamic structured knowledge flow to drive subtask execution and reasoning. FlowSearch is capable of strategically planning and expanding the knowledge flow to enable parallel exploration and hierarchical task decomposition, while also adjusting the knowledge flow in real time based on feedback from intermediate reasoning outcomes and insights. FlowSearch achieves competitive performance on both general and scientific benchmarks, including GAIA, HLE, GPQA and TRQA, demonstrating its effectiveness in multi-disciplinary research scenarios and its potential to advance scientific discovery. The code is available at https://github.com/InternScience/InternAgent.
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。