Not Every Rubric Teaches Equally: Policy-Aware Rubric Rewards for RLVR

arXiv:2610.02824v1 Announce Type: new Abstract: Rubric-based reinforcement learning extends reward-driven optimization to open-ended tasks by assigning partial credit to

arXiv:2605.08354v1 Announce Type: new Abstract: Aligning multimodal generative models with human preferences demands reward signals that respect the compositional,

arXiv:2605.01327v1 Announce Type: new Abstract: Existing reinforcement learning approaches for Large Language Models typically perform policy optimization at the granularity of

arXiv:2603.18859v1 Announce Type: new Abstract: Reinforcement learning (RL) holds significant promise for enhancing the agentic reasoning capabilities of large language models

arXiv:2603.26535v1 Announce Type: new Abstract: We propose Process-Aware Policy Optimization (PAPO), a method that integrates process-level evaluation into Group Relative Policy

arXiv:2606.31392v1 Announce Type: new Abstract: Tool-augmented vision-language models (VLMs) can solve multimodal, multi-step tasks by calling external tools, yet they remain

arXiv:2603.25133v1 Announce Type: new Abstract: Rubric-based evaluation has become a prevailing paradigm for evaluating instruction following in large language models (LLMs).

arXiv:2608.27505v2 Announce Type: cross Abstract: Reinforcement learning from human feedback (RLHF) has become the dominant paradigm for aligning large language models (LLMs) with