Derives new loss functions for SFT and RL that optimize directly for test-time inference operators like aggregation or filtering, with empirical gains in scaling.
Does reinforcement learning really incentivize reasoning capacity in LLMs beyond the base model? InAdvances in Neural Information Processing Systems, 2025
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Compute Aligned Training: Optimizing for Test Time Inference
Derives new loss functions for SFT and RL that optimize directly for test-time inference operators like aggregation or filtering, with empirical gains in scaling.