# Emergent Communication with World Models

arXiv: https://arxiv.org/abs/2002.09604 · HTML: https://mlsanity.com/paper/2002.09604/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in World models for language agents, one of 11 directions in World models.
- Builds on 3 of its 26 references that are in the map.
- First posted on arXiv 22 Feb 2020.

## Placed in

- World models / [World models for language agents](https://mlsanity.com/wm/world-models-for-language-agents/)

## Builds on (most cited first, 3 of 3)

- [World Models](https://mlsanity.com/paper/1803.10122/) (2018)
- [Learning Latent Dynamics for Planning from Pixels](https://mlsanity.com/paper/1811.04551/) (2018)
- [Recurrent World Models Facilitate Policy Evolution](https://mlsanity.com/paper/1809.01999/) (2018)

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

- [A Survey of Multi-Agent Deep Reinforcement Learning with Communication](https://mlsanity.com/paper/2203.08975/) (2022)
- [A Review of the Applications of Deep Learning-Based Emergent Communication](https://mlsanity.com/paper/2407.03302/) (2024)
- [Generative Emergent Communication: Large Language Model is a Collective World Model](https://mlsanity.com/paper/2501.00226/) (2024)
- [Language-Guided World Models: A Model-Based Approach to AI Control](https://mlsanity.com/paper/2402.01695/) (2024)
- [Multi-Agent Curricula and Emergent Implicit Signaling](https://mlsanity.com/paper/2106.11156/) (2021)
- [Symbol Emergence as Inter-personal Categorization with Head-to-head Latent Word](https://mlsanity.com/paper/2205.15027/) (2022)
- [Symbol emergence as interpersonal cross-situational learning: the emergence of lexical knowledge with combinatoriality](https://mlsanity.com/paper/2306.15837/) (2023)

## Abstract (arXiv)

We introduce Language World Models, a class of language-conditional generative model which interpret natural language messages by predicting latent codes of future observations. This provides a visual grounding of the message, similar to an enhanced observation of the world, which may include objects outside of the listening agent's field-of-view. We incorporate this "observation" into a persistent memory state, and allow the listening agent's policy to condition on it, akin to the relationship between memory and controller in a World Model. We show this improves effective communication and task success in 2D gridworld speaker-listener navigation tasks. In addition, we develop two losses framed specifically for our model-based formulation to promote positive signalling and positive listening. Finally, because messages are interpreted in a generative model, we can visualize the model beliefs to gain insight into how the communication channel is utilized.