Post-Reasoning boosts LLM accuracy by reversing the usual answer-after-reasoning order, delivering mean relative gains of 17.37% across 117 model-benchmark pairs with zero extra cost.
Title resolution pending
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
representative citing papers
GRLO shows RLHF from scratch on 5K open-ended prompts raises average performance from 24.1 to 63.1 across domains on Qwen3-4B-Base using 46x less data and 68x less compute than in-domain RLVR while remaining competitive with heavily post-trained models.
Recovering an orthogonal basis from model activations yields a model-native skill characterization that improves reasoning Pass@1 by up to 41% via targeted data selection and supports inference steering, outperforming human-characterized alternatives.
Math reasoning gains in LLMs rarely transfer to general domains; RL tuning generalizes while SFT causes forgetting and representation drift.
citing papers explorer
-
GRLO: Towards Generalizable Reinforcement Learning in Open-Ended Environments from Zero
GRLO shows RLHF from scratch on 5K open-ended prompts raises average performance from 24.1 to 63.1 across domains on Qwen3-4B-Base using 46x less data and 68x less compute than in-domain RLVR while remaining competitive with heavily post-trained models.