Skip to content

Author

Jaehoon Kim

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint May 2026

Hindsight Compacts but Does Not Repair: Rethinking On-Policy Self-Distillation in Reasoning Models

It is hypothesized that in long traces, hindsight reveals which steps were unnecessary more readily than which steps would have repaired the solution, and that changing the divergence, enriching or reinjecting the privileged context, and training longer only move OPSD along the same accuracy-length tradeoff.

Jaehoon Kim, Dong-Ha Lee · 4 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.