MonoScale: Scaling Multi-Agent System with Monotonic Improvement

TL;DR

MonoScale is a framework that enables scalable multi-agent systems by ensuring performance improves monotonically as new agents are added, using a trust-region memory update mechanism.

Contribution

It introduces a novel expansion-aware update method that maintains performance guarantees during multi-agent system scaling.

Findings

Stable performance gains as agent pool expands

Outperforms naive scale-up and fixed-pool baselines

Formalizes augmentation as a contextual bandit

Abstract

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.