AgentFugue: 通过集体推理实现长周期任务的智能体扩展

摘要

近期长周期智能体任务的进展主要依赖于通过增强模型、优化工具及构建更有效框架来纵向扩展单个智能体。相比之下，关于横向扩展的研究则少得多：即多个面向同一任务的对等智能体，能否在不依赖明确角色分工或工作流编排的情况下，成为额外的能力来源。我们针对这一问题展开研究，并提出AgentFugue——一种围绕共享推理中枢构建的集体推理框架。当对等智能体并行探索同一任务时，中枢会记录每个智能体已确认、尝试或排除的简洁笔记，使各智能体能够以当前搜索所需的形式选择性地获取其他智能体的发现。该设计将原本孤立的轨迹转化为可复用中间推理的互联生态，无需集中式规划。我们将中枢实现为可插拔的通信层，并通过监督微调和端到端强化学习进行训练。在研究的具有挑战性的长周期场景中，AgentFugue显著优于强基线模型。研究结果表明，集体推理能将横向扩展的对等智能体系统转化为独立的能力增益来源，而不仅仅是增加计算开销的手段。

English

Recent progress on long-horizon agentic tasks has been driven largely by scaling up individual agents through stronger models, better tools, and more effective scaffolding. In contrast, much less is understood about scaling out: whether multiple peer agents, all targeting the same task, can become an additional source of capability without relying on explicit role specialization or workflow orchestration. We study this question and propose AgentFugue, a collective reasoning framework built around a shared reasoning hub. As peer agents explore the same task in parallel, the hub records concise notes on what each agent has established, attempted, or ruled out, and enables each agent to selectively access what other agents have discovered in a form useful for its current search. This design turns otherwise isolated trajectories into a connected ecology of reusable intermediate reasoning without requiring centralized planning. We instantiate the hub as a plug-in communication layer, trained with supervised fine-tuning and end-to-end reinforcement learning. Across the challenging long-horizon settings we study, AgentFugue improves over strong baselines. Our results suggest that collective reasoning can turn scaling out peer agent systems into a distinct source of capability gains, rather than merely a way of spending more compute.