{"work":{"id":"7e929792-6a2a-42ff-a1db-763f890d8b4e","openalex_id":null,"doi":null,"arxiv_id":"2502.01600","raw_key":null,"title":"Reinforcement learning for long-horizon interactive llm agents.arXiv preprint arXiv:2502.01600, 2025","authors":null,"authors_text":"Kevin Chen, Marco Cusumano-Towner, Brody Huval, Aleksei Petrenko, Jack- son Hamburger, Vladlen Koltun, and Philipp Krähenbühl","year":2025,"venue":null,"abstract":null,"external_url":"https://arxiv.org/abs/2502.01600","cited_by_count":null,"metadata_source":"arxiv_reference","metadata_fetched_at":"2026-05-22T21:22:09.371843+00:00","pith_arxiv_id":null,"created_at":"2026-05-09T06:40:40.593347+00:00","updated_at":"2026-05-22T21:22:09.371843+00:00","title_quality_ok":true,"display_title":"arXiv preprint arXiv:2502.01600 , year=","render_title":"arXiv preprint arXiv:2502.01600 , year="},"hub":{"state":{"work_id":"7e929792-6a2a-42ff-a1db-763f890d8b4e","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":19,"external_cited_by_count":null,"distinct_field_count":5,"first_pith_cited_at":"2025-04-02T23:51:27+00:00","last_pith_cited_at":"2026-05-19T16:19:29+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":"2026-06-02T19:55:02.404211+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":7}],"polarity_counts":[{"context_polarity":"background","n":5},{"context_polarity":"unclear","n":2}],"runs":{},"summary":{},"graph":{},"authors":[]}}