{"work":{"id":"09e9aeff-7314-468c-b3c4-e45fe4def91a","openalex_id":null,"doi":null,"arxiv_id":"2505.19255","raw_key":null,"title":"Vtool-r1: Vlms learn to think with images via reinforcement learning on multimodal tool use.arXiv preprint arXiv:2505.19255, 2025","authors":null,"authors_text":"Mingyuan Wu, Jingcheng Yang, Jize Jiang, Meitang Li, Kaizhuo Yan, Hanchao Yu, Minjia Zhang, Chengxiang Zhai, and Klara Nahrstedt","year":2025,"venue":null,"abstract":null,"external_url":"https://arxiv.org/abs/2505.19255","cited_by_count":null,"metadata_source":"arxiv_reference","metadata_fetched_at":"2026-05-22T07:51:15.305870+00:00","pith_arxiv_id":null,"created_at":"2026-05-11T04:41:00.034648+00:00","updated_at":"2026-05-22T07:51:15.305870+00:00","title_quality_ok":true,"display_title":"Vtool-r1: Vlms learn to think with images via reinforcement learning on multimodal tool use","render_title":"Vtool-r1: Vlms learn to think with images via reinforcement learning on multimodal tool use"},"hub":{"state":{"work_id":"09e9aeff-7314-468c-b3c4-e45fe4def91a","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":11,"external_cited_by_count":null,"distinct_field_count":3,"first_pith_cited_at":"2025-09-02T17:46:26+00:00","last_pith_cited_at":"2026-05-21T15:47:41+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":"2026-06-05T08:38:40.287133+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":2},{"context_role":"baseline","n":1},{"context_role":"dataset","n":1}],"polarity_counts":[{"context_polarity":"background","n":2},{"context_polarity":"baseline","n":1},{"context_polarity":"use_dataset","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}