Tag
提出 Tool-Augmented Strategic Agent (TASA)，通过总结和利用优化轨迹、结合策略引导的自适应工具规划，提升 LLM 基于提示的组合优化（OPRO）的可追溯性与解质量。
This paper presents an automated agentic approach using Large Language Models to synthesize interpretable Python feature extractors for algorithm selection in constraint satisfaction problems, outperforming expert-curated methods.