Amer Goel, Yeganeh Alimohammadi, Andrew Daw · 2026 · arXiv
DOI: 10.48550/arXiv.2610.26819 · open-access PDF
Реальные проблемы принятия решений сочетают в себе два качественно разных типа ограничений: требования, которые должны быть удовлетворены, называемые жесткими ограничениями, и предпочтения, которые могут быть нарушены, называемые мягкими ограничениями. Поскольку эти проблемы часто ставятся для лиц, принимающих решения на естественном языке, большие языковые модели предлагают естественный инструмент для оказания помощи в их решении.
Machine translation (Meta M2M100); the English original follows.
Real-world decision problems combine two qualitatively different kinds of constraints: requirements that must be satisfied, called hard constraints, and preferences that can be violated, called soft constraints. Because these problems are often posed to decision-makers in natural language, large language models offer a natural tool for assisting with their solution. This has given rise to autoformulation, which focuses on using LLMs to translate natural-language descriptions of decision problems into executable mathematical optimization models. However, this research often neglects soft constr
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.26819, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange