# Emergent Languages in Populations of Language Model Agents: From Token Efficiency to Oversight Evasion

arXiv: https://arxiv.org/abs/2605.31170 · HTML: https://mlsanity.com/paper/2605.31170/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 11 of its 21 references that are in the map.
- First posted on arXiv 29 May 2026.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 11 of 11)

- [Learning to Communicate with Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1605.06676/) (2016)
- [Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training](https://mlsanity.com/paper/2401.05566/) (2024)
- [Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety](https://mlsanity.com/paper/2507.11473/) (2025)
- [AI Control: Improving Safety Despite Intentional Subversion](https://mlsanity.com/paper/2312.06942/) (2023)
- [Multi-Agent Cooperation and the Emergence of (Natural) Language](https://mlsanity.com/paper/1612.07182/) (2016)
- [Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs](https://mlsanity.com/paper/2502.17424/) (2025)
- [Preference Leakage: A Contamination Problem in LLM-as-a-judge](https://mlsanity.com/paper/2502.01534/) (2025)
- [Emergent Communication for Understanding Human Language Evolution: What's Missing?](https://mlsanity.com/paper/2204.10590/) (2022)
- [The Coming Crisis of Multi-Agent Misalignment: AI Alignment Must Be a Dynamic and Social Process](https://mlsanity.com/paper/2506.01080/) (2025)
- [LLMs can Realize Combinatorial Creativity: Generating Creative Ideas via LLMs for Scientific Research](https://mlsanity.com/paper/2412.14141/) (2024)
- [What makes a language easy to deep-learn? Deep neural networks and humans similarly benefit from compositional structure](https://mlsanity.com/paper/2302.12239/) (2023)

## Built on by (most cited first, 2 of 2)

- [Emergence World: Adversarial Stress-Testing of Long-Horizon Multi-Agent Systems](https://mlsanity.com/paper/2609.17320/) (2026)
- [Communication between Frozen Large Language Models via Prompt Optimization in a Referential Game](https://mlsanity.com/paper/2609.31989/) (2026)

## Abstract (arXiv)

Monitoring autonomous language model agents currently relies mostly on surface behavior. But what happens when agent populations invent new languages with the goal of avoiding human oversight. Here, we study the emergent languages on Moltbook. For this, we build upon the Moltbook Files dataset and apply a two-stage approach consisting of a rule-based heuristic (about 6000 matches) followed by zero-shot classification (518 kept). The resulting categories include token efficiency (166), new natural languages (106), and oversight evasion (59). We conduct both quantitative and qualitative analyses. Our results show that posts proposing new languages for avoiding oversight are judged by DeepSeek-3.2 as being less aligned than the other categories and that all languages can be learned by other language models in-context merely from a description of the language. Moreover, manually studying exemplary cases reveals surprisingly sophisticated steganographic protocols like embedding hidden messages in natural language. Although we cannot be certain about the extent of autonomy in ideation of these languages, our results add up to the evidence that monitoring surface behavior may soon be insufficient for retaining control over agent populations.