# From Signals to Structure: How Memory Architecture Drives Language Emergence in LLM Agents

arXiv: https://arxiv.org/abs/2607.00233 · HTML: https://mlsanity.com/paper/2607.00233/

## Key facts

- Cited by 4 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 14 of its 25 references that are in the map.
- First posted on arXiv 30 Jun 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, 14 of 14)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Show Your Work: Scratchpads for Intermediate Computation with Language Models](https://mlsanity.com/paper/2112.00114/) (2021)
- [Playing repeated games with Large Language Models](https://mlsanity.com/paper/2305.16867/) (2023)
- [Multi-Agent Cooperation and the Emergence of (Natural) Language](https://mlsanity.com/paper/1612.07182/) (2016)
- [Emergent social conventions and collective bias in LLM populations](https://mlsanity.com/paper/2410.08948/) (2024)
- [Emergence of Linguistic Communication from Referential Games with Symbolic and Pixel Input](https://mlsanity.com/paper/1804.03984/) (2018)
- [Compositional Languages Emerge in a Neural Iterated Learning Model](https://mlsanity.com/paper/2002.01365/) (2020)
- [On the Pitfalls of Measuring Emergent Communication](https://mlsanity.com/paper/1903.05168/) (2019)
- [Ease-of-Teaching and Language Structure from Emergent Communication](https://mlsanity.com/paper/1906.02403/) (2019)
- [Capacity, Bandwidth, and Compositionality in Emergent Language Learning](https://mlsanity.com/paper/1910.11424/) (2019)
- [Searching for Structure: Investigating Emergent Communication with Large Language Models](https://mlsanity.com/paper/2412.07646/) (2024)
- [Toward a Theory of Hierarchical Memory for Language Agents](https://mlsanity.com/paper/2603.21564/) (2026)
- [LoopBench: Discovering Emergent Symmetry Breaking Strategies with LLM Swarms](https://mlsanity.com/paper/2512.13713/) (2025)

## Built on by (most cited first, 4 of 4)

- [GlossoGen: Emergent Language in Complex Multi-Agent LLM Interactions](https://mlsanity.com/paper/2609.01491/) (2026)
- [Despite Instructions: Frontier Agents Improvise Covert Channels at Test Time](https://mlsanity.com/paper/2609.32701/) (2026)
- [Memory Is Communication: The Frontier Between Remembering and Signaling](https://mlsanity.com/paper/2608.17053/) (2026)
- [Communication between Frozen Large Language Models via Prompt Optimization in a Referential Game](https://mlsanity.com/paper/2609.31989/) (2026)

## Abstract (arXiv)

How do two agents invent a shared language from scratch? In a Lewis signaling game, a sender and receiver must coordinate on a code using only their interaction history. We study five memory architectures across varying channel configurations with LLM agents and find that memory architecture matters more than channel capacity. Agents with a persistent private notebook benefit from surplus channel capacity and avoid the high-capacity collapse seen in stateless agents, achieving the most reliable coordination (0.867 ± 0.023 at capacity = 25). Stateless agents peak at moderate capacity and then degrade as the vocabulary grows beyond what a rolling context window can track The notebook externalizes learned conventions, freeing agents from having to re-derive codes each round. An information bottleneck-inspired argument predicts an optimal capacity equal to the number of objects. Instead, the bottleneck (capacity = 8) proves to be a fragility point, and surplus capacity is generally better. We show that channel capacity alone cannot predict coordination; memory architecture determines whether agents turn interaction history into stable conventions, and both dimensions are needed to understand how signals become language.