{"ID":2883850,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.08147","arxiv_id":"2508.08147","title":"From Natural Language to Solver-Ready Power System Optimization: An LLM-Assisted, Validation-in-the-Loop Framework","abstract":"This paper introduces a novel Large Language Models (LLMs)-assisted agent that automatically converts natural-language descriptions of power system optimization scenarios into compact, solver-ready formulations and generates corresponding solutions. In contrast to approaches that rely solely on LLM to produce solutions directly, the proposed method focuses on discovering a mathematically compatible formulation that can be efficiently solved by off-the-shelf optimization solvers. Directly using LLMs to produce solutions often leads to infeasible or suboptimal results, as these models lack the numerical precision and constraint-handling capabilities of established optimization solvers. The pipeline integrates a domain-aware prompt and schema with an LLM, enforces feasibility through systematic validation and iterative repair, and returns both solver-ready models and user-facing results. Using the unit commitment problem as a representative case study, the agent produces optimal or near-optimal schedules along with the associated objective costs. Results demonstrate that coupling the solver with task-specific validation significantly enhances solution reliability. This work shows that combining AI with established optimization frameworks bridges high-level problem descriptions and executable mathematical models, enabling more efficient decision-making in energy systems","short_abstract":"This paper introduces a novel Large Language Models (LLMs)-assisted agent that automatically converts natural-language descriptions of power system optimization scenarios into compact, solver-ready formulations and generates corresponding solutions. In contrast to approaches that rely solely on LLM to produce solutions...","url_abs":"https://arxiv.org/abs/2508.08147","url_pdf":"https://arxiv.org/pdf/2508.08147v1","authors":"[\"Yunkai Hu\",\"Tianqiao Zhao\",\"Meng Yue\"]","published":"2025-08-11T16:22:57Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}