Smaller models provide temporally correlated policy-level diversity that serves as structured exploration for training larger models in GRPO, yielding accuracy gains such as +8.8% on AIME 24 with reduced compute via the S2L-PO framework.
arXiv preprint arXiv:2503.20194 , year=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
SelectiveRM applies optimal transport with a joint consistency discrepancy and partial mass relaxation to produce reward models that optimize a tighter upper bound on clean risk while autonomously dropping noisy preference samples.
Multi-agent deep research systems self-optimize prompts through self-play to match or outperform expert-crafted versions.
citing papers explorer
-
Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO
Smaller models provide temporally correlated policy-level diversity that serves as structured exploration for training larger models in GRPO, yielding accuracy gains such as +8.8% on AIME 24 with reduced compute via the S2L-PO framework.
-
Optimal Transport for LLM Reward Modeling from Noisy Preference
SelectiveRM applies optimal transport with a joint consistency discrepancy and partial mass relaxation to produce reward models that optimize a tighter upper bound on clean risk while autonomously dropping noisy preference samples.
-
Self-Optimizing Multi-Agent Systems for Deep Research
Multi-agent deep research systems self-optimize prompts through self-play to match or outperform expert-crafted versions.