Abstract
Multi-agent frameworks built on large language models (LLMs) routinely entangle three logically distinct concerns: who is on the team (organization), how members align (coordination), and which algorithm fuses their work (collaboration protocol).
IMACS (Intelligent Multi-Agent Collaboration System) separates these into orthogonal, independently swappable layers. Classic organizational theory (Belbin roles, Mintzberg coordination, RACI accountability) becomes executable, validated configuration, while the framework places six published collaboration algorithms behind a common interface, exposing roles, coordination, and accountability as independently configurable factors.
We use this separation to conduct controlled comparisons in which organizational assignments vary while the collaboration protocol is held fixed. It also turns protocol choice into a variable that can be learned: Adaptive Org Routing, a contextual-bandit meta-protocol, selects a protocol per task under an explicit quality-cost tradeoff, outperforming every fixed protocol in a controlled study and training online on real benchmark and LLM-judge rewards.
The ablations expose a mechanism. Accountability placement changes outcomes exactly when the protocol routes the deliverable through the accountable agent, and the winning placement flips across model families, so organizational design cannot be hard-coded; it must be revalidated or learned for each model binding.
Blogger's Review: The IMACS framework proposed in this paper provides a fresh perspective on designing multi-agent systems by decoupling organizational structure, coordination methods, and algorithm selection. The adaptive routing mechanism significantly enhances collaborative efficiency, warranting further exploration and application in future research.