| title | Dynamic Latent Routing |
|---|---|
| authors | Fangyuan Yu, Xin Su, Amir Abdullah |
| date | 2026-05-14 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2605.14323 |
| affiliation | Thoughtworks |
| upvotes | 3 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf |
| abstract | We investigate the temporal concatenation of sub-policies in Markov Decision Processes (MDP) with time-varying reward functions. We introduce General Dijkstra Search (GDS), and prove that globally optimal goal-reaching policies can be recovered through temporal composition of intermediate optimal sub-policies. Motivated by the "search, select, update" principle underlying GDS, we propose Dynamic Latent Routing (DLR), a language-model post-training method that jointly learns discrete latent codes, routing policies, and model parameters through dynamic search in a single training stage. In low-data fine-tuning settings, DLR matches or outperforms supervised fine-tuning across four datasets and six models, achieving a mean gain of +6.6 percentage points, while prior discrete-latent baselines consistently underperform SFT. Mechanistic analyses and targeted code ablations show that DLR learns structured routing behaviors with distinct causal roles. |
cite
@misc{yu2026dynamic,
title={Dynamic Latent Routing},
author={Fangyuan Yu and Xin Su and Amir Abdullah},
year={2026},
eprint={2605.14323},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2605.14323}
}