用多智能体强化学习实现信息搜索的并行扩展，性能媲美超大单模型。
WideSeek-R1: Exploring Width Scaling for Broad Information Seeking via Multi-Agent Reinforcement Learning
- 设计分层多智能体架构，通过强化学习协同调度并行子代理。
- 在2万条广义信息检索任务上，40亿参数模型达40.0%物品F1得分。
- 支持横向扩展，子代理越多性能越强，适合复杂搜索场景。
近年来大语言模型的发展主要聚焦于深度扩展，即单一智能体通过多轮推理与工具使用解决长周期问题。然而，当任务范围扩大时，核心瓶颈从个体能力转向组织能力。本文探索多智能体系统的宽度扩展，以应对广义信息搜索需求。现有系统常依赖人工设计的工作流与轮换交互，难以有效并行化。为此，我们提出WideSeek-R1，一种基于多智能体强化学习（MARL）训练的主代理-子代理框架，实现可扩展的编排与并行执行。通过共享大模型但隔离上下文，并结合专用工具，WideSeek-R1在2万条广义信息寻求任务的标注数据集上联合优化主代理与并行子代理。大量实验表明，WideSeek-R1-4B在WideSearch基准上达到40.0%的物品F1分数，性能与单代理的DeepSeek-R1-671B相当。此外，随着并行子代理数量增加，其性能持续提升，验证了宽度扩展的有效性。
原文摘要 · Abstract (English)
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.
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。