[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-vector-rewards":3},{"tag":4,"articles":10},{"id":5,"name":6,"slug":7,"article_count":8,"description_zh":9,"description_en":9},"d77bdbb2-21a5-4e18-9520-a66792af0fd0","vector rewards","vector-rewards",0,null,[11],{"id":12,"slug":13,"title":14,"summary":15,"category":16,"image_url":17,"cover_image":17,"language":18,"created_at":19},"08e121ad-d16a-4f61-a124-0530101f4665","vector-policy-optimization-search-diversity-en","Vector Policy Optimization boosts search diversity","VPO trains language models to produce diverse solutions that work better in test-time search.","research","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1779432356045-kl6u.png","en","2026-05-22T06:45:30.65682+00:00"]