文本理解提升WikiRace表现
Textual understanding boost in the WikiRace
AI总结：
针对WikiRace游戏的目标导向导航任务，系统评估结构、语义及混合策略，发现结合循环避免的纯贪心语义相似性引导策略成功率100%且效率远超其他方法，凸显大语言模型的语义导航潜力。
摘要：
WikiRace游戏要求玩家仅通过超链接在维基百科文章间导航，是复杂信息网络中目标导向搜索的有力基准。本文对该任务的导航策略进行系统评估，比较了基于图论结构（介数中心性）、语义（语言模型嵌入）及混合方法的智能体。通过在大型维基百科子图上的严格基准测试，我们证明仅由文章标题语义相似性引导的纯贪心智能体效果极佳。结合简单的循环避免机制后，该策略成功率达100%，导航效率比结构或混合方法高一个数量级。研究结果凸显纯结构启发式在目标导向搜索中的局限性，强调大语言模型作为复杂信息空间中强大零样本语义导航器的变革潜力。
英文摘要：
The WikiRace game, where players navigate between Wikipedia articles using only hyperlinks, serves as a compelling benchmark for goal-directed search in complex information networks. This paper presents a systematic evaluation of navigation strategies for this task, comparing agents guided by graph-theoretic structure (betweenness centrality), semantic meaning (language model embeddings), and hybrid approaches. Through rigorous benchmarking on a large Wikipedia subgraph, we demonstrate that a purely greedy agent guided by the semantic similarity of article titles is overwhelmingly effective. This strategy, when combined with a simple loop-avoidance mechanism, achieved a perfect success rate and navigated the network with an efficiency an order of magnitude better than structural or hybrid methods. Our findings highlight the critical limitations of purely structural heuristics for goal-directed search and underscore the transformative potential of large language models to act as powerful, zero-shot semantic navigators in complex information spaces.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
