用推理规划取代盲目试错，让大模型自动设计更优的组合优化启发式算法。
PathWise: Planning through World Model for Automated Heuristic Design via Self-Evolving LLMs
- 将启发式生成建模为可回溯的决策过程，利用知识图谱保存历史路径。
- 在多种组合优化问题上收敛更快，且能适应不同规模和模型底座。
- 适合需要自动化算法设计的研究者，尤其关注高效求解复杂优化问题。
大型语言模型（LLMs）已推动组合优化问题（COPs）的自动化启发式设计（AHD），但现有框架依赖固定演化规则和静态提示模板，常导致短视生成、冗余评估及对新启发式如何推导的推理不足。本文提出一种新型多智能体推理框架——通过世界模型进行自演化大模型的启发式设计规划（PathWise），将启发式生成视为一个基于蕴含图（entailment graph）的序列决策过程，该图作为搜索轨迹的紧凑状态记忆。策略智能体规划演化动作，世界模型智能体生成条件性启发式演进路径，评判智能体提供路由反馈以总结过往经验。此方法使基于LLM的AHD从试错进化转向有状态的推理规划。在多种COP上的实验表明，PathWise能更快收敛至更优启发式，具备跨不同LLM底座的泛化能力，并可扩展至更大规模问题。
原文摘要 · Abstract (English)
Large Language Models (LLMs) have enabled automated heuristic design (AHD) for combinatorial optimization problems (COPs), but existing frameworks' reliance on fixed evolutionary rules and static prompt templates often leads to myopic heuristic generation, redundant evaluations, and limited reasoning about how new heuristics should be derived. We propose a novel multi-agent reasoning framework, referred to as Planning through World Model for Automated Heuristic Design via Self-Evolving LLMs (PathWise), which formulates heuristic generation as a sequential decision process over an entailment graph serving as a compact, stateful memory of the search trajectory. This approach allows the system to carry forward past decisions and reuse or avoid derivation information across generations. A policy agent plans evolutionary actions, a world model agent generates heuristic rollouts conditioned on those actions, and critic agents provide routed reflections summarizing lessons from prior steps, shifting LLM-based AHD from trial-and-error evolution toward state-aware planning through reasoning. Experiments across diverse COPs show that PathWise converges faster to better heuristics, generalizes across different LLM backbones, and scales to larger problem sizes.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。