{"work":{"id":"4820f50e-98c1-439f-89eb-e74ebe6bbb59","openalex_id":null,"doi":null,"arxiv_id":"2406.13542","raw_key":null,"title":"Self-play with execution feedback: Improving instruction-following capabilities of large language models","authors":null,"authors_text":"Guanting Dong, Keming Lu, Chengpeng Li, Tingyu Xia, Bowen Yu, Chang Zhou, and Jingren Zhou","year":2025,"venue":null,"abstract":null,"external_url":"https://arxiv.org/abs/2406.13542","cited_by_count":null,"metadata_source":"arxiv_reference","metadata_fetched_at":"2026-05-23T06:25:27.817839+00:00","pith_arxiv_id":null,"created_at":"2026-05-10T05:25:54.230465+00:00","updated_at":"2026-05-23T06:25:27.817839+00:00","title_quality_ok":true,"display_title":"Self-play with execution feedback: Improving instruction-following capabilities of large language models","render_title":"Self-play with execution feedback: Improving instruction-following capabilities of large language models"},"hub":{"state":{"work_id":"4820f50e-98c1-439f-89eb-e74ebe6bbb59","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":10,"external_cited_by_count":null,"distinct_field_count":5,"first_pith_cited_at":"2024-12-19T17:56:09+00:00","last_pith_cited_at":"2026-05-11T03:17:31+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":"2026-05-23T18:24:35.870438+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":2},{"context_role":"method","n":1}],"polarity_counts":[{"context_polarity":"background","n":2},{"context_polarity":"use_method","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}