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

1Key Takeaways

• arXiv:2607.00233v1 Announce Type: new Abstract: 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….