{"work":{"id":"7bec1034-d193-4a7e-9ffc-5caa0ac1c47e","openalex_id":null,"doi":null,"arxiv_id":"2503.15478","raw_key":null,"title":"Sweet-rl: Training multi-turn llm agents on collaborative reasoning tasks.arXiv preprint arXiv:2503.15478, 2025","authors":null,"authors_text":"Yifei Zhou, Song Jiang, Yuandong Tian, Jason Weston, Sergey Levine, Sainbayar Sukhbaatar, and Xian Li","year":2025,"venue":null,"abstract":null,"external_url":"https://arxiv.org/abs/2503.15478","cited_by_count":null,"metadata_source":"arxiv_reference","metadata_fetched_at":"2026-05-22T05:34:40.518051+00:00","pith_arxiv_id":null,"created_at":"2026-05-11T00:05:49.998110+00:00","updated_at":"2026-06-05T21:23:00.469572+00:00","title_quality_ok":true,"display_title":"Sweet-rl: Training multi-turn llm agents on collaborative reasoning tasks","render_title":"Sweet-rl: Training multi-turn llm agents on collaborative reasoning tasks"},"hub":{"state":{"work_id":"7bec1034-d193-4a7e-9ffc-5caa0ac1c47e","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":13,"external_cited_by_count":null,"distinct_field_count":4,"first_pith_cited_at":"2025-09-02T17:46:26+00:00","last_pith_cited_at":"2026-05-21T09:46:25+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":"2026-06-11T10:37:58.294519+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":3}],"polarity_counts":[{"context_polarity":"background","n":3}],"runs":{},"summary":{},"graph":{},"authors":[]}}