# GlossoGen: Emergent Language in Complex Multi-Agent LLM Interactions

arXiv: https://arxiv.org/abs/2609.01491 · HTML: https://mlsanity.com/paper/2609.01491/

## Key facts

- Cited by 1 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 36 of its 101 references that are in the map.
- First posted on arXiv 1 Sep 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, 30 of 36)

- [Competition-Level Code Generation with AlphaCode](https://mlsanity.com/paper/2203.07814/) (2022)
- [ALFWorld: Aligning Text and Embodied Environments for Interactive Learning](https://mlsanity.com/paper/2010.03768/) (2020)
- [Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation](https://mlsanity.com/paper/2503.11926/) (2025)
- [Learning Multiagent Communication with Backpropagation](https://mlsanity.com/paper/1605.07736/) (2016)
- [TextWorld: A Learning Environment for Text-based Games](https://mlsanity.com/paper/1806.11532/) (2018)
- [COGS: A Compositional Generalization Challenge Based on Semantic Interpretation](https://mlsanity.com/paper/2010.05465/) (2020)
- [Multi-Agent Cooperation and the Emergence of (Natural) Language](https://mlsanity.com/paper/1612.07182/) (2016)
- [Constrained Language Models Yield Few-Shot Semantic Parsers](https://mlsanity.com/paper/2104.08768/) (2021)
- [Taken out of context: On measuring situational awareness in LLMs](https://mlsanity.com/paper/2309.00667/) (2023)
- [Emergence of Language with Multi-agent Games: Learning to Communicate with Sequences of Symbols](https://mlsanity.com/paper/1705.11192/) (2017)
- [Secret Collusion among AI Agents: Multi-Agent Deception via Steganography](https://mlsanity.com/paper/2402.07510/) (2024)
- [Compositionality and Generalization in Emergent Languages](https://mlsanity.com/paper/2004.09124/) (2020)
- [How Well Can LLMs Negotiate? NegotiationArena Platform and Analysis](https://mlsanity.com/paper/2402.05863/) (2024)
- [Me, Myself, and AI: The Situational Awareness Dataset (SAD) for LLMs](https://mlsanity.com/paper/2407.04694/) (2024)
- [Compositional Languages Emerge in a Neural Iterated Learning Model](https://mlsanity.com/paper/2002.01365/) (2020)
- [Preventing Language Models From Hiding Their Reasoning](https://mlsanity.com/paper/2310.18512/) (2023)
- [minicons: Enabling Flexible Behavioral and Representational Analyses of Transformer Language Models](https://mlsanity.com/paper/2203.13112/) (2022)
- [Hidden in Plain Text: Emergence & Mitigation of Steganographic Collusion in LLMs](https://mlsanity.com/paper/2410.03768/) (2024)
- [Collab-Overcooked: Benchmarking and Evaluating Large Language Models as Collaborative Agents](https://mlsanity.com/paper/2502.20073/) (2025)
- [Do Large Language Models Have Compositional Ability? An Investigation into Limitations and Scalability](https://mlsanity.com/paper/2407.15720/) (2024)
- [CooperBench: Why Coding Agents Cannot be Your Teammates Yet](https://mlsanity.com/paper/2601.13295/) (2026)
- [Learning to Communicate to Solve Riddles with Deep Distributed Recurrent Q-Networks](https://mlsanity.com/paper/1602.02672/) (2016)
- [Large Linguistic Models: Investigating LLMs' metalinguistic abilities](https://mlsanity.com/paper/2305.00948/) (2023)
- [Talk Less, Interact Better: Evaluating In-context Conversational Adaptation in Multimodal LLMs](https://mlsanity.com/paper/2408.01417/) (2024)
- [Bias Amplification in Language Model Evolution: An Iterated Learning Perspective](https://mlsanity.com/paper/2404.04286/) (2024)
- [Searching for Structure: Investigating Emergent Communication with Large Language Models](https://mlsanity.com/paper/2412.07646/) (2024)
- [Revisiting Compositional Generalization Capability of Large Language Models Considering Instruction Following Ability](https://mlsanity.com/paper/2506.15629/) (2025)
- [Post-training for Efficient Communication via Convention Formation](https://mlsanity.com/paper/2508.06482/) (2025)
- [Success and Cost Elicit Convention Formation for Efficient Communication](https://mlsanity.com/paper/2510.24023/) (2025)
- [Noticing the Watcher: LLM Agents Can Infer CoT Monitoring from Blocking Feedback](https://mlsanity.com/paper/2603.16928/) (2026)

## Built on by (most cited first, 1 of 1)

- [Despite Instructions: Frontier Agents Improvise Covert Channels at Test Time](https://mlsanity.com/paper/2609.32701/) (2026)

## Abstract (arXiv)

The growing rate at which LLM agents interact with one another raises key questions about language evolution in multi-LLM-agent settings, with implications for safety and monitorability as well as for linguistic accounts of LLMs. To address these questions, we introduce GlossoGen, a novel platform for studying multi-agent language evolution in complex scenarios. Within GlossoGen, we build the SaveVeyru scenario, which requires agents with partial information to communicate under pressure. We find that language evolution does occur between LLM agents, that the resulting languages are compositional and morphologically productive, and that they deviate from the LLMs' English prior in ways that render them incomprehensible to humans. Moreover, we identify several qualities essential to this evolution: pressure towards efficiency; the strength of the models backing the agents; and access to a "postmortem" stage in which agents can agree on linguistic conventions. Importantly, we observe that different conditions govern the transmission of language to new agents. Specifically, we find that agents learn new languages from usage alone, take an active role in this learning, and that while stronger models are required for novel language emergence, weaker models can learn an existing language once it has emerged. Taken together, our results indicate that current LLMs have the potential for cumulative cultural evolution -- previously attested only in humans -- with mixed populations of agents developing capacities that go beyond their lowest common denominator.