Logi

LLM agents are writing English (…) documents, ostensibly for human review and consumption, but 90%+ of what I have my LLM agents write is exclusively consumed by other agents, … and accessed by other agents - it seems like the English translation is pretty useless for that layer …

But remember, the LLM is trained on human language. It doesn’t understand what it is talking about, it just simulates humans talking about it. I don’t think there is a more fundamental token stream there to be uncovered.

That’s identifying a problem. Then various solutions need to be proposed and their interactions with other parts of the system considered. If it’s as trivial as “make them lighter” then perhaps that’s it. But very often there is a lot more to implementing the chosen solution.