{"work":{"id":"4df9a4a1-3908-4d16-9c0b-253bb245a0c4","openalex_id":null,"doi":null,"arxiv_id":"2510.11370","raw_key":null,"title":"Stabilizing moe reinforcement learning by aligning training and inference routers.arXiv preprint arXiv:2510.11370, 2025","authors":null,"authors_text":"Wenhan Ma, Hailin Zhang, Liang Zhao, Yifan Song, Yudong Wang, Zhifang Sui, and Fuli Luo","year":2025,"venue":null,"abstract":null,"external_url":"https://arxiv.org/abs/2510.11370","cited_by_count":null,"metadata_source":"arxiv_reference","metadata_fetched_at":"2026-07-09T22:26:37.153429+00:00","pith_arxiv_id":null,"created_at":"2026-05-11T09:16:03.303583+00:00","updated_at":"2026-07-09T22:26:37.153429+00:00","title_quality_ok":true,"display_title":"Stabilizing MoE Reinforcement Learning by Aligning Training and Inference Routers","render_title":"Stabilizing MoE Reinforcement Learning by Aligning Training and Inference Routers"},"hub":{"state":{"work_id":"4df9a4a1-3908-4d16-9c0b-253bb245a0c4","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":16,"external_cited_by_count":null,"distinct_field_count":5,"first_pith_cited_at":"2026-01-26T05:12:05+00:00","last_pith_cited_at":"2026-07-08T04:21:42+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-08-23T23:39:59.160038+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":3},{"context_role":"method","n":1}],"polarity_counts":[{"context_polarity":"background","n":4}],"runs":{},"summary":{},"graph":{},"authors":[]}}