G2RPO-A adaptively shortens or lengthens the ground-truth reasoning guidance injected into GRPO rollouts, yielding mostly higher math and code accuracy for small language models than vanilla GRPO.
Deepseek-coder: When the large language model meets programming-the rise of code intelligence
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
G$^2$RPO-A: Guided Group Relative Policy Optimization with Adaptive Guidance
G2RPO-A adaptively shortens or lengthens the ground-truth reasoning guidance injected into GRPO rollouts, yielding mostly higher math and code accuracy for small language models than vanilla GRPO.