# A Batch of Mixture-of-Experts Papers Targets Routing as the Next Efficiency Lever

Three preprints published the same day attack expert routing from different angles: byte-level allocation, task-aware fine-tuning supervision, and interpreting what routed reward models actually reward.

- Published: 2026-08-10T06:21:58.349Z
- Canonical: https://polylog.news/ai/2026-08-10/a-batch-of-mixture-of-experts-papers-targets-routing-as-the
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [arXiv cs.AI](https://arxiv.org/abs/2608.06398), [arXiv cs.CL](https://arxiv.org/abs/2608.06396), [arXiv cs.AI](https://arxiv.org/abs/2608.06400)

Three preprints posted to arXiv on the same day treat mixture-of-experts (MoE) routing as unfinished business rather than a solved architectural choice. EntropyMoE addresses byte-level models that skip the tokenizer by grouping bytes into d…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-08-10/a-batch-of-mixture-of-experts-papers-targets-routing-as-the (subscription information: https://polylog.news/pricing).