A step-level reward framework using GPT-4o as a training-time verifier reduces reasoning errors in small language models on physics benchmarks by 10-20% over baselines.
Two thin lenses separated by distance d: 1 F = 1 f1 + 1 f2 −d f1f2 f1 f2 d 3.3: Optical Instruments Simple microscope: m =D/f in normal adjustment
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Reason, Reward, Refine: Step-Level Errors Corrections with Structured Feedback for Physics Reasoning in Small Language Models
A step-level reward framework using GPT-4o as a training-time verifier reduces reasoning errors in small language models on physics benchmarks by 10-20% over baselines.