# TriRoute Proposes One Learned Router for Experts, Depth, and KV-Cache at Once

The method jointly allocates mixture-of-experts, layer-skipping, and key-value cache budget per token, targeting the conditional-computation gains that current techniques capture only one axis at a time.

- Published: 2026-07-09T05:32:14.424Z
- Canonical: https://polylog.news/ai/2026-07-09/triroute-proposes-one-learned-router-for-experts-depth-and-k
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [arXiv (TriRoute)](https://arxiv.org/abs/2607.06601)

A paper introducing TriRoute argues that conditional computation, spending more compute on hard tokens and less on easy ones, is being underused because the leading techniques each act on a single axis. Mixture-of-Experts sparsifies the fee…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-07-09/triroute-proposes-one-learned-router-for-experts-depth-and-k (subscription information: https://polylog.news/pricing).