arXiv AI July 22, 2026 By Jinbiao Nie, Kewei Feng, Xiaoyuan Zhang, Shan Yin, Zizhuo Wang, Bin Dong

MILP-Evo: Closed-Loop Fully Automatic Design of MILP Solvers

arXiv:2607. 18252v1 Announce Type: new Abstract: Machine learning methods have shown that data-driven policies can accelerate mixed-integer linear programming (MILP) solvers, but many such approaches remain difficult to inspect, adapt, and deploy because the learned policy is represented as an external predictor or other opaque model.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv Machine Learning

Jul 31

FunL2O: LLM-Guided Feature Function Design for Learning to Optimize

arXiv:2607. 27389v1 Announce Type: new Abstract: Learning-to-optimize (L2O) methods accelerate repeated optimization by training models to predict solutions, warm starts, branching decisions, or other forms of solver guidance.

By Bingheng Li, Junyang Cai, Yupeng Zhang, Bistra Dilkina, Jayant Kalagnanam, Dzung T. Phan

llms

arXiv AI

Aug 6

Improving Auto-Design of Neural PDE Solvers with a Domain-Specific Language

arXiv:2608. 04384v1 Announce Type: new Abstract: Neural PDE solver auto-design is fundamentally a search-space representation problem.

By Shengxin Kong, Liwen Xu, Jingwen Fu

llms agents benchmarks

arXiv AI

Jul 22

PEARL: Solver-in-the-Loop Interactive Optimization Modeling from Natural Language

arXiv:2607. 18256v1 Announce Type: new Abstract: Optimization modeling is the process of translating real-world decision problems, often described in natural language, into formal mathematical formulations and executable solver code.

By Hongliang Lu, Zhong Li, Yuxuan Chen, Yuan Lan, Fan Zhang, Zaiwen Wen

llms benchmarks

arXiv AI

Aug 5

Don't Regenerate, Debug: A Domain-Specific Agent for Repairing Near-Miss Hardware Operators

arXiv:2608. 02712v1 Announce Type: cross Abstract: Kernel generation for hardware accelerators such as GPUs and NPUs has become a proving ground for large language models (LLMs), and state-of-the-art systems raise correctness through pipelines that couple LLMs with agentic reinforcement learning and evolutionary search.

By Yansong Sun, Shenxiu Wu, Siyuan Chen, Runlin Hou, Junhao Qiu, Junming Cao, Shudi Shao, Zhichao Lu, Qingfu Zhang

llms rag agents reinforcement-learning benchmarks

arXiv AI

Aug 10

Not All Problems Are Best Modeled as MILP: A DSL-Centric Framework for Flexible and Accurate Optimization Modeling

arXiv:2608. 07040v1 Announce Type: new Abstract: Solving combinatorial optimization problems (COPs) requires not only efficient algorithms but also carefully crafted formulations.

By Shaofeng Zhang, Hongyuan Su, Qingwen Peng, Zefang Zong, Shengcai Liu, Ke Tang, Yong Li

llms benchmarks

arXiv AI

Aug 11

Improving Constraint Models with LLM Agents

arXiv:2608. 08127v1 Announce Type: new Abstract: The runtime of Constraint Programming (CP) solvers is highly sensitive to modeling choices, such as symmetry breaking, implied constraints, global constraints, constraint reformulation, and variable representation.

By Florentina Voboril, Stefan Szeider

llms agents

Related stories

FunL2O: LLM-Guided Feature Function Design for Learning to Optimize

Improving Auto-Design of Neural PDE Solvers with a Domain-Specific Language

PEARL: Solver-in-the-Loop Interactive Optimization Modeling from Natural Language

Don't Regenerate, Debug: A Domain-Specific Agent for Repairing Near-Miss Hardware Operators

Not All Problems Are Best Modeled as MILP: A DSL-Centric Framework for Flexible and Accurate Optimization Modeling

Improving Constraint Models with LLM Agents