{"work":{"id":"0b9c0950-4be9-4a42-a77f-55c8e4a80b1e","openalex_id":"https://openalex.org/W4407806895","doi":"10.48550/arxiv.2502.14499","arxiv_id":"2502.14499","raw_key":null,"title":"MLGym : A new framework and benchmark for advancing AI research agents, 2025","authors":null,"authors_text":"Deepak Nathani, Lovish Madaan, Nicholas Roberts, Nikolay Bashlykov, Ajay Menon, Vincent Moens, Amar Budhiraja, Despoina Magka, Vladislav Vorotilov, Gaurav Chaurasia, Dieuwke Hupkes, Ricardo Silveira Cabral, Tatiana Shavrina, Jakob Foerster,","year":2025,"venue":"ArXiv.org","abstract":null,"external_url":"https://arxiv.org/abs/2502.14499","cited_by_count":4,"metadata_source":"arxiv_reference","metadata_fetched_at":"2026-08-05T02:28:24.338817+00:00","pith_arxiv_id":null,"created_at":"2026-05-09T22:13:58.359409+00:00","updated_at":"2026-08-05T02:28:24.338817+00:00","title_quality_ok":true,"display_title":"Mlgym: A new framework and benchmark for advancing ai research agents","render_title":"Mlgym: A new framework and benchmark for advancing ai research agents"},"hub":{"state":{"work_id":"0b9c0950-4be9-4a42-a77f-55c8e4a80b1e","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":18,"external_cited_by_count":4,"distinct_field_count":4,"first_pith_cited_at":"2025-04-28T11:08:22+00:00","last_pith_cited_at":"2026-06-23T12:58:23+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":"2026-08-22T04:09:53.049088+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":4},{"context_role":"dataset","n":2}],"polarity_counts":[{"context_polarity":"background","n":5},{"context_polarity":"use_dataset","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}