{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T00:12:25Z","timestamp":1783037545797,"version":"3.54.6"},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"1","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AAAI-SS"],"abstract":"<jats:p>Quantum annealing offers a promising paradigm for solving\nNP-hard combinatorial optimization problems, but its\npractical application is severely hindered by two\nchallenges: the complex, manual process of translating\nproblem descriptions into the requisite Quadratic\nUnconstrained Binary Optimization (QUBO) format and the\nscalability limitations of current quantum hardware. To\naddress these obstacles, we propose a novel end-to-end\nframework, LLM-QUBO, that automates this entire\nformulation-to-solution pipeline. Our system leverages a\nLarge Language Model (LLM) to parse natural language,\nautomatically generating a structured mathematical\nrepresentation. To overcome hardware limitations, we\nintegrate a hybrid quantum-classical Benders' decomposition\nmethod. This approach partitions the problem, compiling the\ncombinatorial complex master problem into a compact QUBO\nformat, while delegating linearly structured sub-problems\nto classical solvers. The correctness of the generated QUBO\nand the scalability of the hybrid approach are validated\nusing classical solvers, establishing a robust performance\nbaseline and demonstrating the framework's readiness for\nquantum hardware. Our primary contribution is a synergistic\ncomputing paradigm that bridges classical AI and quantum\ncomputing, addressing key challenges in the practical\napplication of optimization problem. This automated\nworkflow significantly reduces the barrier to entry,\nproviding a viable pathway to transform quantum devices\ninto accessible accelerators for large-scale, real-world\noptimization challenges.<\/jats:p>","DOI":"10.1609\/aaaiss.v7i1.36913","type":"journal-article","created":{"date-parts":[[2025,11,23]],"date-time":"2025-11-23T08:18:38Z","timestamp":1763885918000},"page":"411-418","source":"Crossref","is-referenced-by-count":1,"title":["LLM-QUBO: An End-to-End Framework for Automated QUBO\nTransformation from Natural Language Problem Descriptions"],"prefix":"10.1609","volume":"7","author":[{"given":"Huixiang","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mahzabeen","family":"Emu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Salimur","family":"Choudhury","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"9382","published-online":{"date-parts":[[2025,11,23]]},"container-title":["Proceedings of the AAAI Symposium Series"],"original-title":[],"link":[{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI-SS\/article\/download\/36913\/39051","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI-SS\/article\/download\/36913\/39051","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,23]],"date-time":"2025-11-23T08:18:38Z","timestamp":1763885918000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI-SS\/article\/view\/36913"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,23]]},"references-count":0,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,11,23]]}},"URL":"https:\/\/doi.org\/10.1609\/aaaiss.v7i1.36913","relation":{},"ISSN":["2994-4317"],"issn-type":[{"value":"2994-4317","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,23]]}}}