{"ID":2866673,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.21404","arxiv_id":"2509.21404","title":"How Large Language Models Need Symbolism","abstract":"We argue that AI's future requires more than scaling. To unlock genuine discovery, large language models need a compass: human-crafted symbols to guide their powerful but blind intuition.","short_abstract":"We argue that AI's future requires more than scaling. To unlock genuine discovery, large language models need a compass: human-crafted symbols to guide their powerful but blind intuition.","url_abs":"https://arxiv.org/abs/2509.21404","url_pdf":"https://arxiv.org/pdf/2509.21404v1","authors":"[\"Xiaotie Deng\",\"Hanyu Li\"]","published":"2025-09-24T15:51:42Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\"]","methods":"[\"Language Model\"]","has_code":false}