Poly-EPO adapts reinforcement learning to train language models on sets of responses that are both accurate and exploratory, yielding better generalization, diversity, and test-time scaling on reasoning benchmarks.
This expands to 25x^2 - 10x + 1 = 9x^2 + 12x + 4
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Poly-EPO: Training Exploratory Reasoning Models
Poly-EPO adapts reinforcement learning to train language models on sets of responses that are both accurate and exploratory, yielding better generalization, diversity, and test-time scaling on reasoning benchmarks.