GlossoGen study shows AI agents evolve and transmit new languages
EliasEskin · x · 2026-09-03
A study with Schmidt Sciences and AE Systems rigorously examines LLM agent language emergence, beyond anecdotal single-run evidence. Key findings: emergence depends on model strength, scratchpad message access, and efficiency pressure; the emergent languages are morphologically productive and compositional; and they can be culturally transmitted to new agents, even weaker models that couldn't develop language themselves. The team built GlossoGen, a platform for controlled, sandboxed multi-agent experiments with configurable initial conditions.
More from Research
- OpenAI repo claims GPT-6-Astra Lean-formalized a prime-gaps bound of 186 — scaling01 · 2026-09-04
- Fable 5.1 found a flaw in Arrhenius's sixth population ethics impossibility theorem — or did it? — birchlse · 2026-09-04
- VRRL: RL with visual feedback teaches VLMs to self-correct their mistakes — gregd_nlp · 2026-09-04
- $11,000 competition launched for AI-generated philosophy papers — davidad · 2026-09-04
- TabArena author on tabular ML: foundation models now default, LLMs surprisingly bad at tables — ziv_ravid · 2026-09-04
- Sentdex shows general multimodal LLMs can drive robots with zero training — Sentdex · 2026-09-04