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

arXiv: https://arxiv.org/abs/2604.12213 · HTML: https://mlsanity.com/paper/2604.12213/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use.
- Builds on 8 of its 15 references that are in the map.
- First posted on arXiv 14 Apr 2026.

## Placed in

- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 8 of 8)

- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [MMBench: Is Your Multi-modal Model an All-around Player?](https://mlsanity.com/paper/2307.06281/) (2023)
- [MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI](https://mlsanity.com/paper/2311.16502/) (2023)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [The Orchestration of Multi-Agent Systems: Architectures, Protocols, and Enterprise Adoption](https://mlsanity.com/paper/2601.13671/) (2026)
- [AgentMaster: A Multi-Agent Conversational Framework Using A2A and MCP Protocols for Multimodal Information Retrieval and Analysis](https://mlsanity.com/paper/2507.21105/) (2025)
- [LLM Agent Communication Protocol (LACP) Requires Urgent Standardization: A Telecom-Inspired Protocol is Necessary](https://mlsanity.com/paper/2510.13821/) (2025)
- [Revisiting Gossip Protocols: A Vision for Emergent Coordination in Agentic Multi-Agent Systems](https://mlsanity.com/paper/2508.01531/) (2025)

## Built on by (most cited first, 1 of 1)

- [Four-Axis Decision Alignment for Long-Horizon Enterprise AI Agents](https://mlsanity.com/paper/2604.19457/) (2026)

## Abstract (arXiv)

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-level reasoning for the benefit to materialize. We present MMA2A, an architecture layer atop A2A that inspects Agent Card capability declarations to route voice, image, and text parts in their native modality. On CrossModal-CS, a controlled 50-task benchmark with the same LLM backend, same tasks, and only the routing path varying, MMA2A achieves 52% task completion accuracy versus 32% for the text-bottleneck baseline (95% bootstrap CI on DeltaTCA: [8, 32] pp; McNemar's exact p = 0.006). Gains concentrate on vision-dependent tasks: product defect reports improve by +38.5 pp and visual troubleshooting by +16.7 pp. This accuracy gain comes at a 1.8× latency cost from native multimodal processing. These results suggest that routing is a first-order design variable in multi-agent systems, as it determines the information available for downstream reasoning.