# Towards Multi-Agent Communication-Based Language Learning

arXiv: https://arxiv.org/abs/1605.07133 · HTML: https://mlsanity.com/paper/1605.07133/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 May 2016.

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

- [Compositional Generalization in Unsupervised Compositional Representation Learning: A Study on Disentanglement and Emergent Language](https://mlsanity.com/paper/2210.00482/) (2022)
- [Towards More Human-like AI Communication: A Review of Emergent Communication Research](https://mlsanity.com/paper/2308.02541/) (2023)
- [Babysit A Language Model From Scratch: Interactive Language Learning by Trials and Demonstrations](https://mlsanity.com/paper/2405.13828/) (2024)
- [An Outlook on the Opportunities and Challenges of Multi-Agent AI Systems](https://mlsanity.com/paper/2505.18397/) (2025)
- [Learning Multi-Object Positional Relationships via Emergent Communication](https://mlsanity.com/paper/2302.08084/) (2023)
- [Context-dependent communication under environmental constraints](https://mlsanity.com/paper/2305.05821/) (2023)
- [Aligned but Not Partner-Specific: Distinguishing How Multimodal LLM Agents Succeed in Reference Games Without Human-Like Conventions](https://mlsanity.com/paper/2606.08081/) (2026)

## Abstract (arXiv)

We propose an interactive multimodal framework for language learning. Instead of being passively exposed to large amounts of natural text, our learners (implemented as feed-forward neural networks) engage in cooperative referential games starting from a tabula rasa setup, and thus develop their own language from the need to communicate in order to succeed at the game. Preliminary experiments provide promising results, but also suggest that it is important to ensure that agents trained in this way do not develop an adhoc communication code only effective for the game they are playing