[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-weak-rewards":3},{"tag":4,"articles":10},{"id":5,"name":6,"slug":7,"article_count":8,"description_zh":9,"description_en":9},"80afe95c-5146-446a-8f62-e1403a831729","weak rewards","weak-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},"3ab37b54-e52b-4118-a61b-b594973b3aa4","weak-rewards-persistent-llm-user-models-en","Weak Rewards for Persistent LLM User Models","This paper explores using weak rewards from retrieval-augmented interaction to model user preferences in chat agents.","research","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1779084841156-q2lt.png","en","2026-05-18T06:13:34.268303+00:00"]