# Low-Bandwidth Communication Emerges Naturally in Multi-Agent Learning Systems

arXiv: https://arxiv.org/abs/2011.14890 · HTML: https://mlsanity.com/paper/2011.14890/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Nov 2020.

## Built on by (most cited first, 7 of 7)

- [A Review of the Applications of Deep Learning-Based Emergent Communication](https://mlsanity.com/paper/2407.03302/) (2024)
- [Learning Multi-Agent Communication with Contrastive Learning](https://mlsanity.com/paper/2307.01403/) (2023)
- [Cooperative Multi-Agent Fairness and Equivariant Policies](https://mlsanity.com/paper/2106.05727/) (2021)
- [Optimization's Neglected Normative Commitments](https://mlsanity.com/paper/2305.17465/) (2023)
- [Responsible Emergent Multi-Agent Behavior](https://mlsanity.com/paper/2311.01609/) (2023)
- [Individual and Collective Autonomous Development](https://mlsanity.com/paper/2109.11223/) (2021)
- [Active Electrosensing and Communication in MARL-trained Weakly Electric Fish Collectives](https://mlsanity.com/paper/2511.08436/) (2025)

## Abstract (arXiv)

In this work, we study emergent communication through the lens of cooperative multi-agent behavior in nature. Using insights from animal communication, we propose a spectrum from low-bandwidth (e.g. pheromone trails) to high-bandwidth (e.g. compositional language) communication that is based on the cognitive, perceptual, and behavioral capabilities of social agents. Through a series of experiments with pursuit-evasion games, we identify multi-agent reinforcement learning algorithms as a computational model for the low-bandwidth end of the communication spectrum.