Modality-Native Routing in Agent-to-Agent Networks: A Multimodal A2A Protocol Extension

ArXi:2604.12213v1 Announce Type: new Preserving multimodal signals across agent boundaries is necessary for accurate cross-modal reasoning, but it is not sufficient. We show that modality-native routing in Agent-to-Agent (A2A) networks improves task accuracy by 20%age points over text-bottleneck baselines, but only when the downstream reasoning agent can exploit the richer context that native routing preserves. An ablation replacing LLM-backed reasoning with keyword matching eliminates the accuracy gap entirely (36% vs.