MAPLE：基于语言与进化的记忆增强规划
MAPLE: Memory-Augmented Planning with Language and Evolution
查看机构详情
- Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
MAPLE通过记忆增强结合语言构建与进化搜索，维护动态优化问题，在NLDO基准上完成全部轨迹并达到高质量，支持快速适应与决策保留。
中文摘要 AI 辅助
领域从业者了解其业务约束，但可能缺乏运筹学专业知识或专门支持。基于LLM的优化智能体将自然语言需求转化为已建立的优化工具可执行的模型或求解器程序。这一进展使优化更加易于使用，但现实世界的运营是动态的：需求、资源和优先级的变化要求对数据、约束和目标进行更新。以孤立请求为中心的方法对快速适应提供的支持有限，而这种适应需要保留早期决策并重用有用的搜索结果。我们提出MAPLE（基于语言与进化的记忆增强规划），一个通过连续自然语言请求维护优化问题的智能体。MAPLE将基于语言的问题构建与数学规划和进化搜索相结合。它保留优化程序、已接受的计划、早期更新以及用于后续请求的候选解决方案。我们引入NLDO，一个包含15条轨迹和180次更新的基准，涵盖选择、排程、排班、路由和云资源放置。在主要评估中，MAPLE完成所有轨迹，实现在线标量质量0.951和帕累托超体积比0.875。受控比较进一步表明，维护可执行状态可提高更新有效性，并能在重大修订中保留有用的搜索信息。
英文摘要
Domain practitioners understand their business constraints but may lack operations-research expertise or dedicated support. LLM-based optimization agents translate natural-language requirements into models or solver programs that established optimization tools can execute. This progress makes optimization more accessible, but real-world operations are dynamic: changing demand, resources, and priorities require updates to data, constraints, and objectives. Methods centered on isolated requests offer limited support for rapid adaptation that preserves earlier decisions and reuses useful search results. We introduce MAPLE (Memory-Augmented Planning with Language and Evolution), an agent for maintaining optimization problems through successive natural-language requests. MAPLE combines language-based problem construction with mathematical programming and evolutionary search. It retains the optimization program, accepted plans, earlier updates, and candidate solutions for subsequent requests. We introduce NLDO, a benchmark of 15 trajectories and 180 updates spanning selection, scheduling, rostering, routing, and cloud-resource placement. In the main evaluation, MAPLE completes all trajectories and achieves online scalar quality of 0.951 and a Pareto hypervolume ratio of 0.875. Controlled comparisons further show that maintaining executable state improves update validity and can preserve useful search information across substantial revisions.
