Learning to Solve and Optimize by Evolving Code
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Evolving Ensemble of Agents
We introduce the Evolving Ensemble of Agents (EvE), a decentralized framework that organizes existing, highly capable coding agents into a live, co-evolving system for algorithmic discovery. Rather than reinventing the w…
ACE: Self-Evolving LLM Coding Framework via Adversarial Unit Test Generation and Preference Optimization
Large Language Models (LLMs) excel at code generation but remain heavily reliant on large-scale annotated solutions and verification-based supervision, which constrains scalability and hinders sustained self-improvement.…
Code GenerationEvolving Algebraic Multigrid Methods Using Grammar-Guided Genetic Programming
Multigrid methods despite being known to be asymptotically optimal algorithms, depend on the careful selection of their individual components for efficiency. Also, they are mostly restricted to standard cycle types like …
CLPO: Curriculum Learning meets Policy Optimization for LLM Reasoning
Online reinforcement learning with verifiable rewards (RLVR) has become an effective paradigm for improving the reasoning abilities of large language models, but most methods still optimize reasoning trajectories over th…
Reinforcement LearningMathematical ReasoningData AugmentationEvolving-RL: End-to-End Optimization of Experience-Driven Self-Evolving Capability within Agents
Experience-driven self-evolving agents aim to overcome the static nature of large language models by distilling reusable experience from past interactions, thus enabling adaptation to novel tasks at deployment time. This…
Reinforcement Learning