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.

翻译：近年来，基于大语言模型的多智能体系统发展迅速，其通常使用路由器来分解任务并将子任务分配给专门的智能体。扩展系统能力的一种自然方式是持续集成新的功能智能体或工具接口以扩大智能体池，但简单的扩展可能导致性能崩溃，因为路由器在面对新加入的、异构且不可靠的智能体时会面临冷启动问题。我们提出MonoScale，这是一个具备扩展意识的更新框架，它能主动生成一小部分针对智能体条件的熟悉化任务，从成功和失败的交互中收集证据，并将其提炼为可审计的自然语言记忆以指导未来的路由决策。我们将序列化增广形式化为一个上下文赌博机问题，并执行信任域记忆更新，从而在智能体加入的各个轮次中保证性能单调非递减。在GAIA和Humanity's Last Exam基准上的实验表明，随着智能体池的扩大，系统性能获得稳定提升，优于简单的扩展方法和基于强路由器的固定智能体池基线。