Communication to Completion: Modeling Collaborative Workflows with Intelligent Multi-Agent Communication

TL;DR

This paper introduces a realistic multi-agent communication framework that models communication costs, leading to improved efficiency and revealing emergent coordination patterns in collaborative workflows.

Contribution

It presents the C2C framework with the Alignment Factor metric, providing a theoretical basis for optimizing multi-agent collaboration considering communication constraints.

Findings

Cost-aware strategies improve efficiency by over 40%.

Emergent hub-and-spoke coordination patterns observed.

Strategies are consistent across multiple AI models.

Abstract

Multi-agent LLM systems have demonstrated impressive capabilities in complex collaborative tasks, yet most frameworks treat communication as instantaneous and free, overlooking a fundamental constraint in real world teamwork, collaboration cost. We propose a scalable framework implemented via Communication to Completion (C2C), which explicitly models communication as a constrained resource with realistic temporal costs. We introduce the Alignment Factor (AF), a dynamic metric inspired by Shared Mental Models, to quantify the link between task understanding and work efficiency. Through experiments on 15 software engineering workflows spanning three complexity tiers and team sizes from 5 to 17 agents, we demonstrate that cost-aware strategies achieve over 40% higher efficiency compared to unconstrained interaction. Our analysis reveals emergent coordination patterns: agents naturally adopt manager centric hub-and-spoke topologies, strategically escalate from asynchronous to synchronous channels based on complexity, and prioritize high value help requests. These patterns remain consistent across multiple frontier models (GPT-5.2, Claude Sonnet 4.5, Gemini 2.5 Pro). This study moves beyond simple agent construction, offering a theoretical foundation for quantifying and optimizing the dynamics of collaboration in future digital workplaces.