GlossoGen Paper Shows LLM Agents Evolve Compositional Languages Incomprehensible to Humans

EliasEskin · x · 2026-09-15

GlossoGen, an arXiv paper backed by Schmidt Sciences' AI Agents pilot program, introduces a platform for studying language evolution among LLM agents via the SaveVeyru scenario, where partially informed agents must communicate under pressure.

Key findings:

The results raise monitorability and safety concerns for multi-agent systems.

Related event: LLM Agents Evolve Their Own Unreadable Language, GlossoGen Study Shows(3 posts)→

Original post →

More from Research

Research channel →