arXiv — cs.AI preprintsInternational9 October 2026
DIAL-OPD: Learning More from Fewer Tokens in On-Policy Distillation
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:2610.11659v1 Announce Type: cross Abstract: On-policy distillation (OPD) supervises student-generated trajectories with token-level teacher signals. Its sampled-token variant avoids the cost of full-vocabulary probabilities. Yet we find that training on fewer tokens can outperform full-token OPD, challenging the intuition that more supervision improves learning. This motivates selecting tokens by learning value. Existing disagreement-based criteria ignore probability scale: tokens assigned negligible probability by both models, termed low-low tokens, can receive large log-ratio rewards a
Read the official announcement
Opens arxiv.org
More from arXiv — cs.AI preprints
- An Explainable Header-Centric Framework for Large-Scale Semantic Table Interpretation and Data Quality Assessment9 October 2026
- Synthesis Through Simulation: Generating Coherent Enterprise Data via Scalable Agent-System Interaction9 October 2026
- Agent-Controlled Forgetting for Tool-Using Agents: Reversible Context Curation in Practice9 October 2026
- Verification and Self-Improvement in Agentic AI: Foundations and Limits9 October 2026
- The Harness as the Only Mutable Surface: Compliance-Bounded Self-Evolution of LLM Agents in Credit Pipelines, with a Measured Admission Gate9 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.