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:
- Language evolution does occur between LLM agents; the resulting languages are compositional and morphologically productive, and drift from the models' English prior in ways incomprehensible to humans.
- Emergence requires efficiency pressure, strong backing models, and a "postmortem" stage for agents to agree on conventions.
- Transmission differs from emergence: stronger models are needed for novel language, but weaker models can learn an existing one from usage alone.
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)→
More from Research
- 2024 survey: 10% AI extinction risk is normal among 1,580 AI researchers — NathanpmYoung · 2026-09-15
- Digital fruit fly brain completes open-world navigation; zebrafish connectome mapping underway at 200TB — udmrzn · 2026-09-15
- AI scores 27M genomic variants across 1,500 cell states, ~40B effects via ENCODE GRAMMAR — anshulkundaje · 2026-09-15
- Brain implant lets paralyzed woman converse in real time via AI-generated voice — Polymarket · 2026-09-15
- Could AI training work like Bitcoin? A compute-voting thought experiment — dbasch · 2026-09-15
- Yandex open-sources its search AI answer model, squeezing 40% more answers from same compute — teortaxesTex · 2026-09-15