# AI Mother Tongue: Self-Emergent Communication in MARL via Endogenous Symbol Systems

arXiv: https://arxiv.org/abs/2507.10566 · HTML: https://mlsanity.com/paper/2507.10566/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 23 references that are in the map.
- First posted on arXiv 7 Jul 2025.

## Builds on (most cited first, 13 of 13)

- [Generating Diverse High-Fidelity Images with VQ-VAE-2](https://mlsanity.com/paper/1906.00446/) (2019)
- [SoundStream: An End-to-End Neural Audio Codec](https://mlsanity.com/paper/2107.03312/) (2021)
- [Learning to Communicate with Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1605.06676/) (2016)
- [Neurosymbolic AI: The 3rd Wave](https://mlsanity.com/paper/2012.05876/) (2020)
- [Learning with Opponent-Learning Awareness](https://mlsanity.com/paper/1709.04326/) (2017)
- [Multi-agent Reinforcement Learning in Sequential Social Dilemmas](https://mlsanity.com/paper/1702.03037/) (2017)
- [SQ-VAE: Variational Bayes on Discrete Representation with Self-annealed Stochastic Quantization](https://mlsanity.com/paper/2205.07547/) (2022)
- [Learning to Incentivize Other Learning Agents](https://mlsanity.com/paper/2006.06051/) (2020)
- [Biases for Emergent Communication in Multi-agent Reinforcement Learning](https://mlsanity.com/paper/1912.05676/) (2019)
- [HQ-VAE: Hierarchical Discrete Representation Learning with Variational Bayes](https://mlsanity.com/paper/2401.00365/) (2023)
- [Neurosymbolic AI -- Why, What, and How](https://mlsanity.com/paper/2305.00813/) (2023)
- [Neuro-Symbolic AI: Explainability, Challenges, and Future Trends](https://mlsanity.com/paper/2411.04383/) (2024)
- [Reward-Independent Messaging for Decentralized Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2505.21985/) (2025)

## Built on by (most cited first, 5 of 5)

- [Safety in Self-Evolving LLM Agent Systems: Threats, Amplification, and Case Studies](https://mlsanity.com/paper/2606.23075/) (2026)
- [Beyond Reward Suppression: Reshaping Steganographic Communication Protocols in MARL via Dynamic Representational Circuit Breaking](https://mlsanity.com/paper/2603.15655/) (2026)
- [Interpretable by AI Mother Tongue: Native Symbolic Reasoning in Neural Models](https://mlsanity.com/paper/2508.18988/) (2025)
- [Probing the Latent World: Emergent Discrete Symbols and Physical Structure in Latent Representations](https://mlsanity.com/paper/2603.20327/) (2026)
- [Auditability Is Not One Property: Rule Overlap, Behavioural Agreement, and Composition in Reinforcement Learning](https://mlsanity.com/paper/2609.28581/) (2026)

## Abstract (arXiv)

In Decentralized Multi-Agent Reinforcement Learning (MARL), the development of Emergent Communication has long been constrained by the ``Joint Exploration Dilemma'', leading agents to fall into a ``Communication Vacuum Equilibrium'' . Traditional methods address this by introducing inductive biases to facilitate communication emergence . This study fundamentally questions whether such artificial inductive biases are, in fact, over-engineering. Through experiments with the ``AI Mother Tongue'' (AIM) framework, based on a Vector Quantized Variational Autoencoder (VQ-VAE), we demonstrate that when agents possess an endogenous symbol system, their neural representations naturally exhibit spontaneous semantic compression and Nash equilibrium-driven semantic convergence, achieving effective symbolic communication without external inductive biases. This aligns with recent neuroscience findings suggesting that the human brain does not directly use human language for internal thought , and resonates with research on ``soft thinking'' capabilities in Large Language Models (LLMs) . Compared to traditional explicit communication methods, AIM demonstrates stronger generality and efficiency. The interpretable analysis toolkit developed in this study confirms that symbol usage exhibits a significant power-law distribution, leading to three major theoretical insights: the ``Neural Communication Hypothesis'', the ``Tool-First Principle'', and the ``Semantic Interpretability Paradigm''. Future research will explore the integration of Hierarchical Quantized Variational Autoencoders (HQ-VAE) to enhance AIM's complex expressive capabilities and investigate the potential for ``Reinforcement Learning (RL) Low-Level Pre-training''. This discovery offers new avenues for bridging symbolism and connectionism.