Retroactive Advantage Correction: Closed-Form V-Trace Bias Correction for Delay-

arXiv:2605.04077v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has become a central paradigm for improving reasoning and code generation

arXiv:2605.06895v1 Announce Type: new Abstract: How can we make models robust to even imperfect human feedback? In reinforcement learning from human feedback (RLHF), human

<!-- SC_OFF --><div class="md"><p>Standard constrained RL assumes consequences are immediate and attributable to the current action. This breaks down whenever violations are

arXiv:2604.09035v1 Announce Type: new Abstract: Model-based reinforcement learning (MBRL) with autoregressive world models suffers from compounding errors, whereas diffusion world