Recent advancements in Large Language Models (LLMs) have largely focused on depth scaling, where a single agent solves long-horizon problems with multi-turn reasoning and tool use. However, as tasks grow broader, the key bottleneck shifts from individual competence to organizational capability. In this work, we explore a complementary dimension of width scaling with multi-agent systems to address broad information seeking. Existing multi-agent systems often rely on hand-crafted workflows and turn-taking interactions that fail to parallelize work effectively. To bridge this gap, we propose WideSeek-R1, a lead-agent-subagent framework trained via multi-agent reinforcement learning (MARL) to synergize scalable orchestration and parallel execution. By utilizing a shared LLM with isolated contexts and specialized tools, WideSeek-R1 jointly optimizes the lead agent and parallel subagents on a curated dataset of 20k broad information-seeking tasks. Extensive experiments show that WideSeek-R1-4B achieves an item F1 score of 40.0% on the WideSearch benchmark, which is comparable to the performance of single-agent DeepSeek-R1-671B. Furthermore, WideSeek-R1-4B exhibits consistent performance gains as the number of parallel subagents increases, highlighting the effectiveness of width scaling.

翻译：近年来，大型语言模型（LLM）的进展主要集中在深度扩展上，即单个智能体通过多轮推理和工具使用来解决长视野问题。然而，随着任务范围变广，关键瓶颈从个体能力转向了组织能力。在本工作中，我们探索了多智能体系统中一种互补的维度——宽度扩展，以应对广泛的的信息寻求任务。现有的多智能体系统通常依赖于手工设计的工作流程和轮流交互，无法有效地并行化工作。为弥补这一差距，我们提出了WideSeek-R1，这是一个通过多智能体强化学习（MARL）训练的领导者-子智能体框架，旨在协同实现可扩展的编排与并行执行。通过利用具有隔离上下文和专用工具的共享LLM，WideSeek-R1在一个包含20k个广泛信息寻求任务的精选数据集上，联合优化了领导者智能体和并行的子智能体。大量实验表明，WideSeek-R1-4B在WideSearch基准测试中取得了40.0%的项目F1分数，其性能可与单智能体DeepSeek-R1-671B相媲美。此外，随着并行子智能体数量的增加，WideSeek-R1-4B展现出持续的性能提升，这突显了宽度扩展的有效性。