让智能体系统扩容时性能不下降，靠的是提前训练熟悉新成员。
MonoScale: Scaling Multi-Agent System with Monotonic Improvement
- 用少量任务预训练新智能体，收集成功失败经验
- 将经验提炼成可追溯的语言记忆，指导后续调度
- 保证每次加人后性能不降，适合大规模智能体部署
近年来，基于大模型的多智能体系统（MAS）快速发展，通过路由器将任务分解并分配给专业智能体。自然扩展方式是持续集成新功能智能体或工具接口，但盲目扩张可能导致路由器在面对新加入的异构、不可靠智能体时冷启动失效，引发性能崩溃。本文提出MonoScale框架，一种面向扩展的更新机制：主动生成少量智能体相关的熟悉化任务，从成功与失败交互中收集证据，并将其提炼为可审计的自然语言记忆，用于指导未来路由决策。将连续扩展建模为上下文相关老虎机问题，采用信任区域记忆更新策略，确保在接入轮次中性能单调不降。在GAIA和Humanity's Last Exam上的实验表明，随着智能体池扩大，系统性能稳定提升，优于简单扩容和强路由器固定池基线。
原文摘要 · Abstract (English)
In recent years, LLM-based multi-agent systems (MAS) have advanced rapidly, using a router to decompose tasks and delegate subtasks to specialized agents. A natural way to expand capability is to scale up the agent pool by continually integrating new functional agents or tool interfaces, but naive expansion can trigger performance collapse when the router cold-starts on newly added, heterogeneous, and unreliable agents. We propose MonoScale, an expansion-aware update framework that proactively generates a small set of agent-conditioned familiarization tasks, harvests evidence from both successful and failed interactions, and distills it into auditable natural-language memory to guide future routing. We formalize sequential augmentation as a contextual bandit and perform trust-region memory updates, yielding a monotonic non-decreasing performance guarantee across onboarding rounds. Experiments on GAIA and Humanity's Last Exam show stable gains as the agent pool grows, outperforming naive scale-up and strong-router fixed-pool baselines.
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。