A progressive three-stage RL framework with medical-specific rewards improves retrieval-augmented reasoning on medical QA benchmarks, reportedly surpassing GPT-4o-mini with an 8B model.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Med-R$^3$: Enhancing Medical Retrieval-Augmented Reasoning of LLMs via Progressive Reinforcement Learning
A progressive three-stage RL framework with medical-specific rewards improves retrieval-augmented reasoning on medical QA benchmarks, reportedly surpassing GPT-4o-mini with an 8B model.