most citedWhen Agents Go Quiet: Output Generation Capacity and Format-Cost Separation for LLM Document Synthesis

3 citations · 3 across the 10 of their papers we have counts for

collaborators
Showing cs.CLShow all

1 paper · 1 filter

cs.CL2026

Entropy Gate: Entropy Quenching for Near-Lossless Token Compression in LLM Pipelines

Justice Owusu Agyemang, Jerry John Kponyo, Kwame Opuni-Boachie Obour Agyekum +3

LLM pipelines waste substantial token budgets on low-information content: repeated context, verbose responses, and redundant boilerplate. We introduce Entropy Gate, a token compres…