Textual understanding boost in the WikiRace

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Ebrahimi, Raman, Fuhrman, Sean, Nguyen, Kendrick, Gurusankar, Harini, Franceschetti, Massimo
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912707336208384
author Ebrahimi, Raman
Fuhrman, Sean
Nguyen, Kendrick
Gurusankar, Harini
Franceschetti, Massimo
author_facet Ebrahimi, Raman
Fuhrman, Sean
Nguyen, Kendrick
Gurusankar, Harini
Franceschetti, Massimo
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_10585
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Textual understanding boost in the WikiRace
Ebrahimi, Raman
Fuhrman, Sean
Nguyen, Kendrick
Gurusankar, Harini
Franceschetti, Massimo
Social and Information Networks
Artificial Intelligence
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.
title Textual understanding boost in the WikiRace
topic Social and Information Networks
Artificial Intelligence
url https://arxiv.org/abs/2511.10585