On-Policy Distillation in Frontier Model Training Isn't a Free Lunch
heghbalz · x · 2026-07-22
As On-Policy Distillation (OPD) becomes a default post-training tool for many open-source frontier models like DeepSeek and MiMO, its potential flaws are surfacing. OPD combines RL's on-policy nature to reduce exposure bias while providing token-level supervision like SFT.
However, an expert points out an inherent failure mode: early mistakes are structurally uncorrectable. When the student model takes an early wrong turn during rollout, the per-token KL divergence computed along that frozen path cannot pull it back. This is proven to be a built-in flaw of the objective function rather than noisy gradients, meaning even a perfect teacher cannot correct this structural learning bias.
More from Research
- ICML 2026 oral paper replication scores stay middling after a stricter re-scoring — profjamesevans · 2026-07-27
- Long-running agents will need immutable event logs, this thread argues — sebpaquet · 2026-07-27
- Seed IQ navigates Doom II, prompting questions about benchmarks beyond ARC-AGI — Fit_Transition8824 · 2026-07-27
- Agentic Data Science in Practice: Agents Write Code but Answer Wrong Questions — hugobowne · 2026-07-27
- A concise canon of foundational papers in ML, systems, NLP, speech, and audio — deliprao · 2026-07-27
- TechCrunch says brain-wave signals could be the next unlock for physical AI training — TechCrunch AI · 2026-07-27