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

Abstract

Abstract: 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 percentage 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. 36\%), establishing a two-layer requirement: protocol-level routing must be paired with capable agent-lev

Research Question

Can SMoES-trained modality routing generalize to other multimodal benchmarks (e.g., DocVQA, InfographicVQA) under domain shift, and how do accuracy and latency trade-offs differ from chart-specific distribution shifts?

Verification Level

Descriptive public verification status only; aggregate claim counts are public, but individual claim records are not exposed here.

Quality Tier

Descriptive public triage only; this tier does not alter current publication or DOI behavior.

Quality Dimensions

Automated triage signals derived from public fields; not human peer review or independent validation.

Correction Record

Public corrections are additive records. Current status does not claim the synthesis is error-free.

Provenance