AI RESEARCH
Athena: Enhancing Multimodal Reasoning with Data-efficient Process Reward Models
arXiv CS.AI
•
ArXi:2506.09532v5 Announce Type: replace-cross We present Athena-PRM, a multimodal process reward model (PRM) designed to evaluate the reward score for each step in solving complex reasoning problems. Developing high-performance PRMs typically demands significant time and financial investment, primarily due to the necessity for step-level annotations of reasoning steps. Conventional automated labeling methods, such as Monte Carlo estimation, often produce noisy labels and incur substantial computational costs.