FlowSearch: Advancing deep research with dynamic structured knowledge flow
This addresses the problem of enabling agentic systems to handle complex, multi-step research tasks, with potential applications in multi-disciplinary scientific discovery, though it appears incremental as it builds on existing multi-agent and knowledge flow concepts.
The paper tackles the challenge of deep research requiring breadth and depth of thinking by proposing FlowSearch, a multi-agent framework that constructs dynamic structured knowledge flows, achieving state-of-the-art performance on benchmarks like GAIA, HLE, GPQA, and TRQA.
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 state-of-the-art 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/Alpha-Innovator/InternAgent.