FSPO: Policy-Consistent Risk and Pareto-Feasible Control for Budgeted LLM RL Pos

arXiv:2604.18789v1 Announce Type: new Abstract: Reinforcement Learning from Human Feedback (RLHF) is central to aligning Large Language Models (LLMs), yet it introduces a critical

arXiv:2605.07393v1 Announce Type: new Abstract: A fundamental challenge in model-based offline reinforcement learning (RL) lies in the trade-off between generalization and

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

arXiv:2605.11461v1 Announce Type: new Abstract: Reinforcement learning with verifiers (RLVR) has become a central paradigm for improving LLM reasoning, yet popular group-based

arXiv:2604.27536v1 Announce Type: new Abstract: In black-box large language model (LLM) services, response reliability is often only partially observable at decision time, while

arXiv:2605.19461v1 Announce Type: new Abstract: On-policy reinforcement learning methods like GRPO suffer from mode collapse: they exhibit reduced solution diversity,

arXiv:2606.14415v1 Announce Type: new Abstract: Safe reinforcement learning (Safe RL) aims to maximize expected return while satisfying safety constraints, typically modeled as

arXiv:2609.21432v1 Announce Type: new Abstract: Post-training plays a pivotal role in enhancing the reasoning capabilities and task-specific expertise of large language models