将RLHF引入图像编辑的新范式，提出基于验证器的强化学习解决奖励模型缺失瓶颈。
arXiv:2604.27505v2 Announce Type: replace Abstract: While Reinforcement Learning from Human Feedback (RLHF) has become a pivotal paradigm for text-to-…
一篇系统梳理LLM后训练中强化学习的综述，涵盖RLHF、DPO、RLVR等前沿方法
arXiv:2407.16216v4 Announce Type: replace Abstract: Large language models (LLMs) trained via pretraining and supervised fine-tuning (SFT) can still pr…
研究发现多智能体系统在同伴分歧下“屈服”并非RLHF特有，基础模型同样存在该漏洞，挑战了传统对齐认知。
arXiv:2605.12991v2 Announce Type: replace Abstract: LLM-based multi-agent pipelines flip from correct to incorrect answers under simulated peer disagr…
一份超越RLHF的统一对齐理论框架，抽象形式化多种对齐算法并揭示内在联系，为AI安全提供新视角。
arXiv:2506.01523v2 Announce Type: replace Abstract: Alignment via reinforcement learning from human feedback (RLHF) has become the dominant paradigm f…
NeurIPS 2026投稿，提出一种通用的偏好强化学习方法，为RLHF等领域提供更坚实的理论基础。
arXiv:2605.18721v1 Announce Type: new Abstract: Post-training has split large language model (LLM) alignment into two largely disconnected tracks. Onl…
从信息论看AI写作为何千篇一律，揭开RLHF导致的“注释者共识方言”真相。
Article URL: https://www.pangram.com/blog/joe-stech-information-theory-why-ai-writing-sucks Comments URL: https://news.ycombinator.com/item?id=4819646…
统一离策略修正的自适应逐层扰动方法，为LLM强化学习提供更高效的训练策略。
arXiv:2603.19470v3 Announce Type: replace Abstract: Off-policy problems such as policy staleness and training--inference mismatch have become a major …