HarnessRL co-evolves open-ended RL rewards with the policy
On Rubric-Mix-10k it beats the strongest baselines by 2.8 to 3.1 points and nearly halves steps to the best checkpoint.
Stories per day · 30 days
3 stories, newest first · one card per story
Stories tagged #rubric-rewards
MetaRubric: Learning to Reward for Rubric-Based Reinforcement Learning
MetaRubric fixes 'Vacuous Credit' in rubric-based RL using counterfactual prompts and evidence-aware scoring, lifting PubMedQA up to 20.4 points.
RULER: Instance-aware Rubric Rewards for SVG Generation
RULER uses per-instruction rubric rewards so reinforcement learning improves text-to-SVG generation without ground truth.