{"ID":2873673,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.05874","arxiv_id":"2509.05874","title":"Learning to Construct Knowledge through Sparse Reference Selection with Reinforcement Learning","abstract":"The rapid expansion of scientific literature makes it increasingly difficult to acquire new knowledge, particularly in specialized domains where reasoning is complex, full-text access is restricted, and target references are sparse among a large set of candidates. We present a Deep Reinforcement Learning framework for sparse reference selection that emulates human knowledge construction, prioritizing which papers to read under limited time and cost. Evaluated on drug--gene relation discovery with access restricted to titles and abstracts, our approach demonstrates that both humans and machines can construct knowledge effectively from partial information.","short_abstract":"The rapid expansion of scientific literature makes it increasingly difficult to acquire new knowledge, particularly in specialized domains where reasoning is complex, full-text access is restricted, and target references are sparse among a large set of candidates. We present a Deep Reinforcement Learning framework for...","url_abs":"https://arxiv.org/abs/2509.05874","url_pdf":"https://arxiv.org/pdf/2509.05874v1","authors":"[\"Shao-An Yin\"]","published":"2025-09-07T00:19:13Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\",\"cs.IR\"]","methods":"[\"Reinforcement Learning\"]","has_code":false}