# Reinforcement Learning Displaces Imitation in Post-Training

Post-training budgets will keep moving from supervised imitation to reinforcement learning against verifiers, because imitation copies surface style and can erode knowledge, which makes verifier construction a recurring competitive asset.

- Conviction: 28 / 100 (weakening)
- 7-day move: -12
- Horizon: Emerging (watchlist)
- Tracking since: 2026-10-05T00:00:00.000Z
- Last updated: 2026-10-12T14:07:13.413Z
- Canonical: https://polylog.news/ai/trends/rl-displaces-imitation-in-post-training
- Publisher: Polylog
- Affected regions: Global

## Recent score history

- 2026-10-11: 30
- 2026-10-12: 28

## Recent evidence

- [neutral] New papers question what reinforcement learning guidance, backdoor leaderboards and summary-tree retrieval actually measure (2026-10-07): A new paper gives a bias-variance theory of when external guidance helps reinforcement learning with verifiable rewards. It describes the conditions under which RL post-training works rather than showing that budgets are moving away from imitation.
- [confirms] Two papers find supervised fine-tuning teaches surface style and can widen a falsification gap that reinforcement learning closes (2026-10-05): One arXiv study explains why supervised fine-tuning causes more forgetting than reinforcement fine-tuning even when every demonstration is correct. A second shows that imitation makes models worse at disproving false theorems, a gap that reinforcement learning closes. Both give direct mechanistic support for moving post-training budgets toward RL against verifiers.