Skip to content

๐Ÿ“ Optimization & Theory

๐Ÿ’ฌ EMNLP2026 ยท 1 paper notes

๐Ÿ“Œ Same area in other venues: ๐Ÿง  NeurIPS2026 (313) ยท ๐ŸŽž๏ธ ECCV2026 (16) ยท ๐Ÿ“ท CVPR2026 (23) ยท ๐Ÿ”ฌ ICLR2026 (225) ยท ๐Ÿงช ICML2026 (91) ยท ๐Ÿค– AAAI2026 (22)

FormuEvo: LLM-Guided Evolution for Discovering Solver-Efficient Mixed-Integer Programming Formulations

FormuEvo reframes mixed-integer programming (MIP) formulation design as an LLM-guided evolutionary search over executable modeling programs, leveraging fine-grained solver statistics as verbal gradients alongside structured memory distillation to achieve up to 5.5x solver speedup over expert designs and prior LLM approaches.