What Do Agents Communicate? Characterizing Information Exchange in Multi-Agent Systems

TL;DR

This paper analyzes the role of information exchange in multi-agent systems using large language models, identifying key factors affecting performance and proposing a technique to improve communication quality.

Contribution

It systematically characterizes inter-agent communication, highlights the importance of reasoning and verification, and introduces Category-Aware Recovery Augmentation to enhance collaboration.

Findings

Absence of reasoning and verification degrades performance.

Proposed technique recovers up to 86.2% of failed cases.

Highlights the importance of information quality in multi-agent systems.

Abstract

Large Language Models (LLMs) have enabled collaborative Multi-Agent (MA) systems, where interacting agents improve performance through diverse reasoning and iterative refinement. However, these systems remain vulnerable to error propagation, where early-stage information degrades downstream reasoning. To address this, we conduct a systematic analysis of inter-agent communication to identify which information drives MA performance. We find that the absence of reasoning and verification in inter-agent communication significantly degrades performance. Based on these insights, we propose Category-Aware Recovery Augmentation (technique), which enforces the presence of critical information during communication. recovers up to 86.2% of failed cases. Our results highlight the key role of information quality in effective MA collaboration. Our code is available at https://anonymous.4open.science/r/cara_mas