发表机构
South China University of Technology; Wuhan University; Sun Yat-Sen University（华南理工大学; 武汉大学; 中山大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对大规模技能库检索易受语义干扰和路由错误的问题，提出基于门控感知蒙特卡洛树搜索的图引导分层检索框架SkillGATE，在六个基准上整体R@1提升16.3%。
AI 中文摘要
技能检索（Skill Retrieval, SR）旨在从外部技能库中识别最相关的技能，随着技能库规模和多样性的增长，这一任务变得日益具有挑战性。现有方法要么独立地对技能进行排序，要么依赖预定义的图传播和分层路由，这使得它们容易受到语义干扰、局部陷阱和早期路由错误的影响。我们将技能检索形式化为一个自适应信息觅食过程，该过程根据搜索过程中观察到的效用和不确定性，协调区域级导航与技能级选择。基于这一形式化，我们提出了SkillGATE，一个带有门控感知蒙特卡洛树搜索（MCTS）的图引导分层检索框架。SkillGATE构建了一个保持图结构的分层索引，并通过选择、扩展、模拟和反向传播执行自适应检索。G-PUCT指导动作选择，扩展探索新区域，模拟评估候选技能，反向传播更新搜索统计信息。在六个技能检索基准上的实验表明，SkillGATE持续改进多种检索和重排序骨干模型，在整体R@1上相比最强的基于检索器的基线实现了16.3%的提升。我们的代码可在https://this https URL获取。
英文摘要
Skill Retrieval (SR) aims to identify the most relevant skills from external skill libraries, and becomes increasingly challenging as libraries grow in scale and diversity. Existing methods either rank skills independently or rely on predefined graph propagation and hierarchical routing, making them vulnerable to semantic distractors, local trapping, and early routing errors. We formulate SR as an adaptive information-foraging process that coordinates region-level navigation with skill-level selection according to the utility and uncertainty observed during search. Based on this formulation, we propose SkillGATE, a graph-guided hierarchical retrieval framework with Gate-Aware Monte Carlo Tree Search (MCTS). SkillGATE constructs a graph-preserving hierarchical index and performs adaptive retrieval through selection, expansion, simulation, and backpropagation. G-PUCT guides action selection, expansion explores new regions, simulation evaluates candidate skills, and backpropagation updates search statistics. Experiments on six SR benchmarks show that SkillGATE consistently improves diverse retrieval and reranking backbones, achieving a 16.3\% improvement in overall R@1 over the strongest retriever-based baseline. Our code is available at https://github.com/Edwinbe/SkillGATE-v1/.
