Expected Reasoning-Step Return Unifies On-Policy Learning from Rewards and Teachers
On-policy reasoning models can learn from task rewards or teacher signals, but these sources differ in form and can favor conflicting updates, leaving unclear which should guide a given reasoning action. We introduce \textbf{Expected Reasoning-Step Return (ERSR)}, which treats semantic reasoning steps as macro-actions and uses Monte Carlo student-policy rollouts to estimate the expected final task reward of student-generated and teacher-proposed actions in a common return space for step-level comparison. ERSR analysis reveals an outcome-dependent asymmetry: student actions are more beneficial than teacher replacements on successful trajectories, whereas teacher replacements become more be...
| Authors | Qiangqiang He, Jin Li |
|---|---|
| Primary category | cs.AI |
| Published | 26 September 2026 |
| Last updated at source | 26 September 2026 |
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.