pith. machine review for the scientific record. sign in

Optimizing language models for inference time objectives using reinforcement learning

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.LG 2

years

2026 2

verdicts

UNVERDICTED 2

representative citing papers

Compute Aligned Training: Optimizing for Test Time Inference

cs.LG · 2026-04-27 · unverdicted · novelty 6.0

Compute Aligned Training derives new loss functions by modeling test-time strategies as operators on the base policy, yielding empirical gains in test-time compute scaling over standard SFT and RL.

citing papers explorer

Showing 2 of 2 citing papers.