# Emergent Language as an Approach to Conscious AI

arXiv: https://arxiv.org/abs/2606.06380 · HTML: https://mlsanity.com/paper/2606.06380/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 36 of its 95 references that are in the map.
- First posted on arXiv 4 Jun 2026.

## Builds on (most cited first, 30 of 36)

- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Asynchronous Methods for Deep Reinforcement Learning](https://mlsanity.com/paper/1602.01783/) (2016)
- [Learning to Communicate with Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1605.06676/) (2016)
- [Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Survey](https://mlsanity.com/paper/2009.13303/) (2020)
- [Emergence of Grounded Compositional Language in Multi-Agent Populations](https://mlsanity.com/paper/1703.04908/) (2017)
- [Experience Grounds Language](https://mlsanity.com/paper/2004.10151/) (2020)
- [Multi-Agent Cooperation and the Emergence of (Natural) Language](https://mlsanity.com/paper/1612.07182/) (2016)
- [Emergence of Language with Multi-agent Games: Learning to Communicate with Sequences of Symbols](https://mlsanity.com/paper/1705.11192/) (2017)
- [The Consciousness Prior](https://mlsanity.com/paper/1709.08568/) (2017)
- [Compositionality and Generalization in Emergent Languages](https://mlsanity.com/paper/2004.09124/) (2020)
- [Tell me about yourself: LLMs are aware of their learned behaviors](https://mlsanity.com/paper/2501.11120/) (2025)
- [Natural Language Does Not Emerge 'Naturally' in Multi-Agent Dialog](https://mlsanity.com/paper/1706.08502/) (2017)
- [Emergent Introspective Awareness in Large Language Models](https://mlsanity.com/paper/2601.01828/) (2026)
- [Compositional Languages Emerge in a Neural Iterated Learning Model](https://mlsanity.com/paper/2002.01365/) (2020)
- [Could a Large Language Model be Conscious?](https://mlsanity.com/paper/2303.07103/) (2023)
- [Emotion Concepts and their Function in a Large Language Model](https://mlsanity.com/paper/2604.07729/) (2026)
- [Capacity, Bandwidth, and Compositionality in Emergent Language Learning](https://mlsanity.com/paper/1910.11424/) (2019)
- [Interpretation of Emergent Communication in Heterogeneous Collaborative Embodied Agents](https://mlsanity.com/paper/2110.05769/) (2021)
- [Large Language Models Report Subjective Experience Under Self-Referential Processing](https://mlsanity.com/paper/2510.24797/) (2025)
- [A Survey of Continual Reinforcement Learning](https://mlsanity.com/paper/2506.21872/) (2025)
- [Language Grounded Multi-agent Reinforcement Learning with Human-interpretable Communication](https://mlsanity.com/paper/2409.17348/) (2024)
- [Emergent Language: A Survey and Taxonomy](https://mlsanity.com/paper/2409.02645/) (2024)
- [Smart Agent-Based Modeling: On the Use of Large Language Models in Computer Simulations](https://mlsanity.com/paper/2311.06330/) (2023)
- [The Five Ws of Multi-Agent Communication: Who Talks to Whom, When, What, and Why -- A Survey from MARL to Emergent Language and LLMs](https://mlsanity.com/paper/2602.11583/) (2026)
- [Learning and communication pressures in neural networks: Lessons from emergent communication](https://mlsanity.com/paper/2403.14427/) (2024)
- [Agnosticism About Artificial Consciousness](https://mlsanity.com/paper/2412.13145/) (2024)
- [The Mechanistic Emergence of Symbol Grounding in Language Models](https://mlsanity.com/paper/2510.13796/) (2025)
- [Unexpected Benefits of Self-Modeling in Neural Systems](https://mlsanity.com/paper/2407.10188/) (2024)
- [A Disproof of Large Language Model Consciousness: The Necessity of Continual Learning for Consciousness](https://mlsanity.com/paper/2512.12802/) (2025)
- [Speaking Your Language: Spatial Relationships in Interpretable Emergent Communication](https://mlsanity.com/paper/2406.07277/) (2024)

## Abstract (arXiv)

The question of whether artificial systems can be conscious remains open, in part because existing approaches either evaluate systems against theory-derived checklists (discriminative) or engineer consciousness-inspired modules directly (architectural); both leave open whether observed structures are artifacts of human language priors. We propose a generative methodology: emergent language (EL) in multi-agent reinforcement learning, where agents start from minimal (no language, no concept of self, minimal exposure to human text) and develop communication under task pressure alone, ensuring causal attributability to task demands rather than inherited human language priors. We position our methodology by discussing how EL serves as a generative tool for studying consciousness-relevant structure, including the role of environment complexity and the interpretation of emergent communication. As a proof of concept, we instantiate this methodology in a minimal environment and show that agents develop self-referential communication, including an echo-mismatch detection circuit that is not predicted by task structure or architecture alone but emerges from a specific environmental affordance.