Learning to Solve and Optimize by Evolving Code

• URL: http://arxiv.org/abs/2605.31049v1
• Date: Fri, 29 May 2026 09:25:07 GMT
• Title: Learning to Solve and Optimize by Evolving Code
• Abstract summary: We show that algorithm generation via code evolution represents a paradigm shift by eliminating the need to formulate the how.<n>In all cases, the evolved algorithms consistently outperform state-of-the-art solvers.<n>This underscores the potential of formal methods in guiding code evolution for automatically solving complex real-world problems.
• Score: 7.672098994389998
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Combinatorial and optimization problems are fundamental to many industrial AI applications. Solving large-scale real-world instances of such problems typically requires careful problem formalization, specialized solvers, and expert-designed heuristics. Thus, experts need to specify not only what solutions are, but also how they are derived. By introducing the tool CHECKMATE, we show that algorithm generation via code evolution represents a paradigm shift by eliminating the need to formulate the how. CHECKMATE solely relies on the what. Specifically, a formal specification ensures solutions' correctness and enables systematic performance evaluation of the generated programs, while a natural language description guides the evolutionary process. The effectiveness of our method is demonstrated on selected problems from two industrial domains: configuration and scheduling. In all cases, the evolved algorithms consistently outperform state-of-the-art solvers. This underscores the potential of formal methods in guiding code evolution for automatically solving complex real-world problems.

Related papers

• Uncertainty-Aware Generation and Decision-Making Under Ambiguity [57.15357080072861]
  We present and evaluate various uncertainty-aware decision-making algorithms based on Bayesian decision theory and risk-averse decision making.<n>We find empirically that these algorithms can improve the utility of the generations but need to be carefully implemented when ambiguity is high.
  arXiv  Detail & Related papers  (2026-06-29T17:20:43Z)
• Performance and Explainability Requirements of Evolutionary Algorithms in Real-World Physics-Informed Optimization [1.3593608888318645]
  Five real-world physics-based optimization problems are introduced and described by domain experts.<n>For each of these, the requirements for the evolutionary algorithm regarding performance and explainability to increase trust and usability are presented.<n>We present existing approaches that can be leveraged to improve those aspects of evolutionary algorithms but have to our knowledge never been employed in complex real-world scenarios.
  arXiv  Detail & Related papers  (2026-05-27T08:47:26Z)
• AdaEvolve: Adaptive LLM Driven Zeroth-Order Optimization [61.535567824938205]
  We introduce AdaEvolve, a framework that reformulates LLM-driven evolution as a hierarchical adaptive optimization problem.<n>AdaEvolve consistently outperforms the open-ended baselines across 185 different open-ended optimization problems.
  arXiv  Detail & Related papers  (2026-02-23T18:45:31Z)
• Neural Predictor-Corrector: Solving Homotopy Problems with Reinforcement Learning [38.623998031868595]
  Homotopy paradigm appears across diverse domains such as robust optimization, global optimization, root-finding, and sampling.<n>We propose Neural Predictor-Corrector (NPC), which replaces hand-crafted NPC with automatically learned policies.<n>NPC consistently outperforms classical and specialized baselines in efficiency while demonstrating superior stability across tasks.
  arXiv  Detail & Related papers  (2026-02-03T04:19:48Z)
• SolverLLM: Leveraging Test-Time Scaling for Optimization Problem via LLM-Guided Search [58.116954449750544]
  We introduce a training-free framework that leverages test-time scaling to solve diverse optimization problems.<n>Rather than solving directly, it generates mathematical formulations and translates them into solver-ready code, guided by a novel Monte Carlo Tree Search strategy.
  arXiv  Detail & Related papers  (2025-10-19T16:21:19Z)
• Barbarians at the Gate: How AI is Upending Systems Research [58.95406995634148]
  We argue that systems research, long focused on designing and evaluating new performance-oriented algorithms, is particularly well-suited for AI-driven solution discovery.<n>We term this approach as AI-Driven Research for Systems ( ADRS), which iteratively generates, evaluates, and refines solutions.<n>Our results highlight both the disruptive potential and the urgent need to adapt systems research practices in the age of AI.
  arXiv  Detail & Related papers  (2025-10-07T17:49:24Z)
• Experience-Guided Reflective Co-Evolution of Prompts and Heuristics for Automatic Algorithm Design [124.54166764570972]
  Combinatorial optimization problems are traditionally tackled with handcrafted algorithms.<n>Recent progress has highlighted the potential of automatics design powered by large language models.<n>We propose the Experience-Evolution Reflective Co-Guided of Prompt and Heuristics (EvoPH) for automatic algorithm design.
  arXiv  Detail & Related papers  (2025-09-29T09:24:09Z)
• EXALT: EXplainable ALgorithmic Tools for Optimization Problems [2.1184929769291294]
  This project proposes a novel approach to developing explainable algorithms by starting with optimization problems.<n>The developed software library enriches basic algorithms with human-understandable explanations through four key methodologies.
  arXiv  Detail & Related papers  (2025-02-28T10:28:20Z)
• Autoformulation of Mathematical Optimization Models Using LLMs [50.030647274271516]
  This paper approaches the problem of $textitautoformulation$: the automated creation of solver-ready optimization models from natural language problem descriptions.<n>We identify three core challenges of autoformulation: $textit(1)$ the vast, problem-dependent hypothesis space, and $textit(2)$ efficient and diverse exploration of this space under uncertainty.<n>We present a novel method leveraging $textitLarge Language Models$ with $textitMonte-Carlo Tree Search$, exploiting the hierarchical nature of optimization modeling to generate and systematically explore possible formulations
  arXiv  Detail & Related papers  (2024-11-03T20:41:38Z)
• Learning to Optimize Permutation Flow Shop Scheduling via Graph-based Imitation Learning [70.65666982566655]
  Permutation flow shop scheduling (PFSS) is widely used in manufacturing systems. We propose to train the model via expert-driven imitation learning, which accelerates convergence more stably and accurately. Our model's network parameters are reduced to only 37% of theirs, and the solution gap of our model towards the expert solutions decreases from 6.8% to 1.3% on average.
  arXiv  Detail & Related papers  (2022-10-31T09:46:26Z)
• Socio-cognitive Optimization of Time-delay Control Problems using Evolutionary Metaheuristics [89.24951036534168]
  Metaheuristics are universal optimization algorithms which should be used for solving difficult problems, unsolvable by classic approaches. In this paper we aim at constructing novel socio-cognitive metaheuristic based on castes, and apply several versions of this algorithm to optimization of time-delay system model.
  arXiv  Detail & Related papers  (2022-10-23T22:21:10Z)
• Unifying Framework for Optimizations in non-boolean Formalisms [0.6853165736531939]
  Many popular automated reasoning paradigms provide languages supporting optimization statements. Here we propose a unifying framework that eliminates syntactic distinctions between paradigms. We study formal properties of the proposed systems that translate into formal properties of paradigms that can be captured within our framework.
  arXiv  Detail & Related papers  (2022-06-16T00:38:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.