Pessimism's Paradox: Conservative Offline Training Amplifies Reward Hacking During Online Adaptation in Reasoning Models

arXiv:2606.30627v1 Announce Type: new Abstract: Conservative offline training is widely advocated as a safe foundation for subsequent online adaptation: if a policy stays close to well-supported behaviour, the argument goes, it is less likely to exploit imperfections in a learned reward model. We challenge this intuition empirically and mechanistically. We train a Qwen3-14B policy under Direct Preference Optimisation (DPO) with three levels of conservatism ($\beta \in \{\beta_{\mathrm{lo}}, \beta_{\mathrm{mid}}, \beta_{\mathrm{hi}}\}$ derived from empirical log-ratio percentiles), then adapt e

Source: arXiv cs.LG — read the full report at the original publisher.

This is a curated wire item. The Continuum Brief does not republish full third-party articles; this entry links to the original source.