HORA adaptively allocates rollouts using hit utility to improve Pass@K over compute-matched GRPO on math reasoning benchmarks while preserving Pass@1.
Differential smooth- ing mitigates sharpening and improves llm reasoning.arXiv preprint arXiv:2511.19942
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 6verdicts
UNVERDICTED 6roles
background 1polarities
background 1representative 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.
HEAL mitigates entropy collapse in few-shot RLVR by selectively adding general-domain data and aligning trajectory-level entropy dynamics, matching full-shot performance with 32 target samples.
Vocabulary dropout prevents diversity collapse in LLM co-evolution by masking proposer logits, yielding average +4.4 point solver gains on mathematical reasoning benchmarks at 8B scale.
Self-training on verified outputs in a free-verifier DSL amplifies performance at pass@8 but does not expand reach, as the base model overtakes at pass@64 across trajectories.
IMAX trains soft prefixes with an InfoMax reward to drive diverse exploration in RLVR, yielding up to 11.60% gains in Pass@4 over standard RLVR across model scales.
citing papers explorer
-
Vocabulary Dropout for Curriculum Diversity in LLM Co-Evolution
Vocabulary dropout prevents diversity collapse in LLM co-evolution by masking proposer logits, yielding average +4.4 point solver gains on mathematical reasoning benchmarks at 8B scale.