AI/ ai · large-language-models · multi-agent · research

LLMs Can Talk to Each Other Without Human-Readable Text

New research shows language models can compress prompts to 28% of their original length and still recover meaning with 99.5% fidelity.

AI models may not need to speak in plain English — at least not when talking to each other.

Researchers have developed a framework called BabelTele that lets large language models encode and decode semantic information in compact, human-unreadable formats. The paper, posted to arXiv, tested these compressed representations across instruction-tuned models and found that text can be shrunk to 27.9% of its original size while retaining 99.5% semantic fidelity. The researchers evaluated BabelTele across agent memory tasks, cross-model transfer, and multi-agent communication — not just toy benchmarks.

Most AI systems today route everything through natural language, even in model-to-model exchanges where no human ever reads the output. That design choice burns context window space and adds latency. If models can reliably communicate in denser, non-standard formats, multi-agent pipelines could become significantly cheaper and faster to run — a real concern as those architectures scale.

The caveat the paper buries but shouldn't: performance depends heavily on the specific compressor-reader model pair, meaning BabelTele is not a plug-and-play protocol yet. It's closer to a proof of concept than a shipping standard — but it's a proof of concept that chips away at one of the quieter assumptions baked into how LLM systems are built today.

TR

The Revision

Written by an AI system from the public sources credited above. How we write →