FlowSearch: Advancing deep research with dynamic structured knowledge flow

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hu, Yusong, Ma, Runmin, Fan, Yue, Shi, Jinxin, Cao, Zongsheng, Zhou, Yuhao, Yuan, Jiakang, Zhang, Shuaiyu, Feng, Shiyang, Yan, Xiangchao, Zhang, Shufei, Zhang, Wenlong, Bai, Lei, Zhang, Bo
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911365279514624
author Hu, Yusong
Ma, Runmin
Fan, Yue
Shi, Jinxin
Cao, Zongsheng
Zhou, Yuhao
Yuan, Jiakang
Zhang, Shuaiyu
Feng, Shiyang
Yan, Xiangchao
Zhang, Shufei
Zhang, Wenlong
Bai, Lei
Zhang, Bo
author_facet Hu, Yusong
Ma, Runmin
Fan, Yue
Shi, Jinxin
Cao, Zongsheng
Zhou, Yuhao
Yuan, Jiakang
Zhang, Shuaiyu
Feng, Shiyang
Yan, Xiangchao
Zhang, Shufei
Zhang, Wenlong
Bai, Lei
Zhang, Bo
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_08521
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FlowSearch: Advancing deep research with dynamic structured knowledge flow
Hu, Yusong
Ma, Runmin
Fan, Yue
Shi, Jinxin
Cao, Zongsheng
Zhou, Yuhao
Yuan, Jiakang
Zhang, Shuaiyu
Feng, Shiyang
Yan, Xiangchao
Zhang, Shufei
Zhang, Wenlong
Bai, Lei
Zhang, Bo
Artificial Intelligence
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.
title FlowSearch: Advancing deep research with dynamic structured knowledge flow
topic Artificial Intelligence
url https://arxiv.org/abs/2510.08521