arXiv — cs.AI preprintsInternational7 October 2026
Rethinking Cross-Tokenizer On-Policy Distillation: From Alignment Coverage to Supervision Reliability
This is an official announcement record
Firsthand records what arXiv — cs.AI preprints announced and links to the original. The wording below is theirs, not ours.
arXiv:2610.08448v1 Announce Type: cross Abstract: On-Policy Distillation (OPD) trains a student on its own generations using teacher feedback. With different tokenizers, comparing teacher and student predictions requires alignment at both sequence and vocabulary levels. In this paper, we examine whether expanding this alignment coverage improves learning. Across three heterogeneous teacher--student pairs on mathematical reasoning and code generation, strict 1:1 groups already cover most student-generated tokens despite substantial vocabulary mismatch. On responses sampled from the students bef
Read the official announcement
Opens arxiv.org
More from arXiv — cs.AI preprints
- GAMEGO: Training Game-Dev Agents with Synthetic Trajectories Anchored in Real-World Assets7 October 2026
- Text2Dashboard: A Governed Agent Architecture for Natural-Language Dashboard Generation over Enterprise DataBrain7 October 2026
- FluidPD: In-Place Elasticity for SLO-Aware Prefill-Decode Disaggregated LLM Serving7 October 2026
- Anchor Divergence for Semantic Geometry in Contrastive Learning7 October 2026
- RadOnc-Agent: An LLM-Orchestrated Framework for AI Workflows Across the Radiotherapy Care Pathway7 October 2026
This content is for informational purposes only and is not professional advice. Specifications, prices, plan tiers, and features change frequently and may differ from what is shown here; verify current details on the manufacturer's or company's official page before purchasing. Ratings are based on analysis of published documentation, not independent lab testing.