Daniel Scalena @danielsc4.it · Oct 16

EAGer works by monitoring token entropy during generation. High entropy token → It branches to explore new paths (reusing prefixes). Token with low entropy → It continues a single path. We cap at M sequences/prompt, saving budget on easy ones without regen. Training-free! 🧵3/

1 likes 1 replies

?

Replies

Daniel Scalena · Oct 16

The fun part: EAGer-adapt reallocates saved budget to "saturating" prompts hitting the M cap, no labels needed! – Training & Verification-Free 🚀 Full EAGer uses labels to catch failing prompts, lowering threshold to branch or add sequences. Great for verifiable pipelines! 🧵4/