提出多智能体架构与基准数据集，推动广度搜索研究发展
WideSeek: Advancing Wide Research via Multi-Agent Scaling
- 构建动态分层多智能体系统，按任务需求并行生成子代理
- 在宽域信息检索任务中，智能体数量增加显著提升搜索覆盖度
- 适合关注智能搜索、多智能体协同与信息整合的研究者
搜索智能正从深度研究转向广度研究，这一范式对在复杂约束下并行获取与整合全面信息至关重要。然而，该领域受限于缺乏专用基准和优化方法。为此，我们从数据管道与智能体优化两方面深入探索：首先，通过多阶段严谨数据流程构建WideSeekBench，一个通用广域信息搜寻（GBIS）基准，确保目标信息量、逻辑约束与领域的多样性；其次，提出WideSeek，一种动态分层多智能体架构，可根据任务需求自主分叉并行子代理；此外，设计统一训练框架，将多智能体轨迹线性化，并使用端到端强化学习优化系统。实验表明，WideSeek与多智能体强化学习有效，证明扩大智能体数量是推进广度研究范式的重要方向。
原文摘要 · Abstract (English)
Search intelligence is evolving from Deep Research to Wide Research, a paradigm essential for retrieving and synthesizing comprehensive information under complex constraints in parallel. However, progress in this field is impeded by the lack of dedicated benchmarks and optimization methodologies for search breadth. To address these challenges, we take a deep dive into Wide Research from two perspectives: Data Pipeline and Agent Optimization. First, we produce WideSeekBench, a General Broad Information Seeking (GBIS) benchmark constructed via a rigorous multi-phase data pipeline to ensure diversity across the target information volume, logical constraints, and domains. Second, we introduce WideSeek, a dynamic hierarchical multi-agent architecture that can autonomously fork parallel sub-agents based on task requirements. Furthermore, we design a unified training framework that linearizes multi-agent trajectories and optimizes the system using end-to-end RL. Experimental results demonstrate the effectiveness of WideSeek and multi-agent RL, highlighting that scaling the number of agents is a promising direction for advancing the Wide Research paradigm.
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。