EDAS modulates advantage signals in RLVR to penalize repeated errors more and rare errors less, yielding consistent gains on math benchmarks when added to existing methods.
Post-training as reweighting: A stochastic view of reasoning trajectories in language models.arXiv preprint arXiv:2511.07368, 2025
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Leveraging Error Diversity in Group Rollouts for Reinforcement Learning
EDAS modulates advantage signals in RLVR to penalize repeated errors more and rare errors less, yielding consistent gains on math benchmarks when added to existing methods.