# Verifiable Semantics for Agent-to-Agent Communication

arXiv: https://arxiv.org/abs/2602.16424 · HTML: https://mlsanity.com/paper/2602.16424/

## Key facts

- Cited by 2 papers in the map (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 5 of its 7 references that are in the map.
- First posted on arXiv 18 Feb 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, 5 of 5)

- [Learning to Communicate with Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1605.06676/) (2016)
- [Emergence of Grounded Compositional Language in Multi-Agent Populations](https://mlsanity.com/paper/1703.04908/) (2017)
- [Multi-Agent Cooperation and the Emergence of (Natural) Language](https://mlsanity.com/paper/1612.07182/) (2016)
- [Stress Testing Deliberative Alignment for Anti-Scheming Training](https://mlsanity.com/paper/2509.15541/) (2025)
- [Unsupervised Translation of Emergent Communication](https://mlsanity.com/paper/2502.07552/) (2025)

## Built on by (most cited first, 2 of 2)

- [Trustworthy Agent Network: Trust in Agent Networks Must Be Baked In, Not Bolted On](https://mlsanity.com/paper/2605.19035/) (2026)
- [Beyond Component Testing: Validating Agentic AI Systems](https://mlsanity.com/paper/2607.29405/) (2026)

## Abstract (arXiv)

Multiagent AI systems require consistent communication, but we lack methods to verify that agents share the same understanding of the terms used. Natural language is interpretable but vulnerable to semantic drift, while learned protocols are efficient but opaque. We propose a certification protocol based on the stimulus-meaning model, where agents are tested on shared observable events and terms are certified if empirical disagreement falls below a statistical threshold. In this protocol, agents restricting their reasoning to certified terms ("core-guarded reasoning") achieve provably bounded disagreement. We also outline mechanisms for detecting drift (recertification) and recovering shared vocabulary (renegotiation). In simulations with varying degrees of semantic divergence, core-guarding reduces disagreement by 72-96%. In a validation with fine-tuned language models, disagreement is reduced by 51%. Our framework provides a first step towards verifiable agent-to-agent communication.