What Do Agents Communicate? Characterizing Information Exchange in Multi-Agent Systems
For researchers building multi-agent LLM systems, this work identifies a key failure mode (error propagation) and provides a method to mitigate it.
The paper analyzes inter-agent communication in LLM-based multi-agent systems, finding that missing reasoning and verification degrades performance. They propose Category-Aware Recovery Augmentation, which recovers up to 86.2% of failed cases.
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