{"entity": "GSPO", "url": "https://wpnews.pro/entity/GSPO", "count": 2, "articles": [{"slug": "vllm-v0-to-v1-correctness-before-corrections-in-rl", "title": "vLLM V0 to V1: Correctness Before Corrections in RL", "url": "https://wpnews.pro/news/vllm-v0-to-v1-correctness-before-corrections-in-rl", "published_at": "2026-05-06 19:06:55+00:00"}, {"slug": "collaborative-reinforcement-learning-why-hacrl-trains-models-in-teams-instead-of", "title": "Collaborative Reinforcement Learning: Why HACRL Trains Models in Teams Instead of Isolation", "url": "https://wpnews.pro/news/collaborative-reinforcement-learning-why-hacrl-trains-models-in-teams-instead-of", "published_at": "2026-03-16 00:00:00+00:00"}]}