Best-of-Depth: Learning Exploratory Dynamics in Looped Transformers

Shota Takashiro, Takeshi Kojima, Masanori Koyama, Kohei Hayashi, Yusuke IwasawaarXiv 2026 · arXiv

Abstract

Looped Transformers extend inference-time computation through repeated latent-state updates, but final-depth training does not directly encourage useful intermediate alternatives. We introduce Best-of-Depth (BoD), which trains a recurrent trajectory as a candidate set by minimizing prediction loss across depths. Different valid targets can be matched at different depths without architectural changes or depth-specific labels. An exact-match analysis connects this objective to solution coverage. On N-Queens completion and graph coloring, BoD improves coverage over final-depth and intermediate-supervision objectives. N-Queens coverage reaches 91.03%, versus 45.75% for final-depth training. Further experiments show discovery beyond the training depth and recovery of solutions withheld from teacher pools on familiar inputs. Fine-tuning a pretrained looped language model with BoD yields higher pooled code-generation success than final-depth training when programs are generated separately at evaluated fixed depths. These results support training recurrent computation for solution discovery along its trajectory.
BibTeX
@misc{takashiro2026best,
  author = {Shota Takashiro and Takeshi Kojima and Masanori Koyama and Kohei Hayashi and Yusuke Iwasawa},
  title = {{Best-of-Depth: Learning Exploratory Dynamics in Looped Transformers}},
  year = {2026},
  eprint = {2611.04663},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2611.04663},
}

Loading related content...

Figure