CoDistill-GRPO lets small and large models mutually improve via co-distillation in GRPO, raising small-model math accuracy by over 11 points while cutting large-model training time by about 18%.
Does Reinforcement Learning Really Incentivize Reasoning Capacity in
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
representative citing papers
UCPO modifies GRPO with a uniformity penalty over correct solutions to prevent diversity collapse in RLVR, yielding up to 10% higher Pass@64 on AIME24 and 45% more equation-level diversity.
ReasoningBank distills generalizable reasoning strategies from agent successes and failures to enable self-evolution, with memory-aware test-time scaling amplifying gains over raw-trajectory or success-only memory on web and software benchmarks.
The power distribution is the target of power sampling, the closed-form solution to self-reward KL-regularized RL, and the basis for power self-distillation that matches sampling performance at lower cost.
citing papers explorer
-
CoDistill-GRPO: A Co-Distillation Recipe for Efficient Group Relative Policy Optimization
CoDistill-GRPO lets small and large models mutually improve via co-distillation in GRPO, raising small-model math accuracy by over 11 points while cutting large-model training time by about 18%.
-
Uniform-Correct Policy Optimization: Breaking RLVR's Indifference to Diversity
UCPO modifies GRPO with a uniformity penalty over correct solutions to prevent diversity collapse in RLVR, yielding up to 10% higher Pass@64 on AIME24 and 45% more equation-level diversity.
-
ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory
ReasoningBank distills generalizable reasoning strategies from agent successes and failures to enable self-evolution, with memory-aware test-time scaling amplifying gains over raw-trajectory or success-only memory on web and software benchmarks.
-
Power Distribution Bridges Sampling, Self-Reward RL, and Self-Distillation
The power distribution is the target of power sampling, the closed-form solution to self-reward KL-regularized RL, and the basis for power self-distillation that matches sampling performance at lower cost.
- Multi-Rollout On-Policy Distillation via Peer Successes and Failures