# Faithful, Not Corrective: Model Capability Governs Message-Format Effects in Multi-Hop Agent Relays

arXiv: https://arxiv.org/abs/2607.09678 · HTML: https://mlsanity.com/paper/2607.09678/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 12 of its 28 references that are in the map.
- First posted on arXiv 12 Jun 2026.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 12 of 12)

- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [Towards a Science of Scaling Agent Systems](https://mlsanity.com/paper/2512.08296/) (2025)
- [A survey of agent interoperability protocols: Model Context Protocol (MCP), Agent Communication Protocol (ACP), Agent-to-Agent Protocol (A2A), and Agent Network Protocol (ANP)](https://mlsanity.com/paper/2505.02279/) (2025)
- [Single-Agent LLMs Outperform Multi-Agent Systems on Multi-Hop Reasoning Under Equal Thinking Token Budgets](https://mlsanity.com/paper/2604.02460/) (2026)
- [KVComm: Enabling Efficient LLM Communication through Selective KV Sharing](https://mlsanity.com/paper/2510.03346/) (2025)
- [Beyond Natural Language: LLMs Leveraging Alternative Formats for Enhanced Reasoning and Communication](https://mlsanity.com/paper/2402.18439/) (2024)
- [The PIMMUR Principles: Ensuring Validity in Collective Behavior of LLM Societies](https://mlsanity.com/paper/2509.18052/) (2025)
- [LLM as a Broken Telephone: Iterative Generation Distorts Information](https://mlsanity.com/paper/2502.20258/) (2025)
- [Toward a Safe Internet of Agents](https://mlsanity.com/paper/2512.00520/) (2025)
- [Natural Language Tools: A Natural Language Approach to Tool Calling In Large Language Agents](https://mlsanity.com/paper/2510.14453/) (2025)
- [Information Fidelity in Tool-Using LLM Agents: A Martingale Analysis of the Model Context Protocol](https://mlsanity.com/paper/2602.13320/) (2026)
- [Lost Before Translation: Social Information Transmission and Survival in AI-AI Communication](https://mlsanity.com/paper/2602.17674/) (2026)

## Abstract (arXiv)

When LLM agents hand information to one another, does the message format matter? Two literatures disagree: format-optimization work reports that structured messages cut cost without hurting accuracy, while format-restriction studies find that imposing structure degrades generation. Neither line has measured what happens when messages traverse multiple hops, where copy fidelity, rather than one-shot generation quality, dominates. We introduce a controlled relay testbed in which briefs of twelve programmatic atomic facts are re-encoded hop by hop in five formats (free natural language, precision-instructed NL, JSON, triples, key-value) over six hops, scored against programmatic ground truth by a fixed strong grader, across two relay-capability tiers, a cognitive-load condition, and a paired-fork error injection. We find that (i) a strong relay is nearly lossless for every format (hop-6 QA recall ≥ 0.973), with residual loss concentrated at the first encoding step; (ii) per-hop cognitive load raises generation cost by 24-53% while fidelity changes stay within ± 1.8 points; (iii) under a weak 1.5B relay, the across-format dispersion of hop-6 recall grows by a factor of 8.7 (CI 5.3-15.5), driven by an encode-drift trade-off that flips the format ranking in transit; and (iv) once an injected error is present, every format propagates it faithfully (surface persistence 83-100%) and no format cascades collateral damage onto neighboring facts. Structure buys a faithful, error-localizing channel, not an error-correcting code.