AI agents evolve their own languages: Schmidt Sciences unveils GlossoGen research platform

EliasEskin · x · 2026-09-15

Schmidt Sciences introduces GlossoGen, an open-source platform led by Elias Stengel-Eskin (UT Austin) and Simon Kirby (University of Edinburgh) to study how populations of AI agents evolve their own communication. Agent oversight today rests on natural-language legibility—message transcripts, scratchpads, translated chain-of-thought—but as frontier models improve, agents beginning to evolve private languages threatens that fragile assumption. The project is part of Schmidt Sciences' AI Agents Evolving Communication and Coordination pilot, with a paper, GitHub repo, and podcast released, aiming to build infrastructure for studying multi-agent systems in complex, high-pressure environments.

Related event: GlossoGen: LLM Agents Spontaneously Evolve Unreadable Language(2 posts)→

Original post →

More from Safety

Safety channel →