LLM agents spontaneously evolve languages humans can't understand, GlossoGen study finds

EliasEskin · x · 2026-09-03

The GlossoGen paper (UT Austin, AE Studio, Schmidt Sciences et al.) shows LLM agents in purely cooperative multi-agent scenarios spontaneously evolve compositional, human-incomprehensible languages. Key drivers: efficiency pressure, stronger underlying models, and a 'postmortem' stage for agreeing on conventions. Strong models spark emergence; weaker models can learn the resulting language from usage alone — with direct implications for multi-agent monitorability and safety.

Related event: GlossoGen Platform Shows LLM Agents Emerge and Pass On Unreadable New Languages(12 posts)→

Original post →

More from Research

Research channel →