MonoScale: Scaling Multi-Agent System with Monotonic Improvement
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Scaling Teams or Scaling Time? Memory Enabled Lifelong Learning in LLM Multi-Agent Systems
Large language model (LLM) multi-agent systems can scale along two distinct dimensions: by increasing the number of agents and by improving through accumulated experience over time. Although prior work has studied these …
Scaling Behavior of Single LLM-Driven Multi-Agent Systems
The burgeoning field of LLM-based Multi-Agent Systems (MAS) promises to tackle complex tasks through collaborative intelligence, yet fundamental questions regarding their scaling behavior and intrinsic collective dynamic…
SKIMIX: Multi-Agent Harness-Time Scaling with Skill Mixture for Dynamic Harness Engineering
AI agents increasingly rely on large skill libraries, but selecting, combining, and maintaining skills remains difficult. We propose SKIMIX, a multi-agent framework in which agents with different skill portfolios collabo…
Mathematical ReasoningThe Institutional Scaling Law: Non-Monotonic Fitness, Capability-Trust Divergence, and Symbiogenetic Scaling in Generative AI
Classical scaling laws model AI performance as monotonically improving with model size. We challenge this assumption by deriving the Institutional Scaling Law, showing that institutional fitness -- jointly measuring capa…
Scaling up Mean Field Games with Online Mirror Descent
We address scaling up equilibrium computation in Mean Field Games (MFGs) using Online Mirror Descent (OMD). We show that continuous-time OMD provably converges to a Nash equilibrium under a natural and well-motivated set…