The Search for Stability: Learning Dynamics of Strategic Publishers with Initial Documents (Abstract Reprint)
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (47) · 39879-39879
DOI: 10.1609/aaai.v40i47.41394 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Omer Madmon und 3 weiteren Autor:innen.
Abstract (Originalsprache)
We study a game-theoretic information retrieval model in which strategic publishers aim to maximize their chances of being ranked first by the search engine while maintaining the integrity of their original documents. We show that the commonly used Probability Ranking Principle (PRP) ranking scheme results in an unstable environment where games often fail to reach pure Nash equilibrium. We propose two families of ranking functions that do not adhere to the PRP. We provide both theoretical and empirical evidence that these methods lead to a stable search ecosystem, by providing positive results on the learning dynamics convergence. We also define the publishers’ and users’ welfare, demonstrate a possible publisher-user trade-off, and provide means for a search system designer to control it. Finally, we show how instability harms long-term users’ welfare.
Zitieren
APA
Madmon, O., Pipano, I., Reinman, I., & Tennenholtz, M. (2026). The Search for Stability: Learning Dynamics of Strategic Publishers with Initial Documents (Abstract Reprint). Proceedings of the AAAI Conference on Artificial Intelligence, 40(47), 39879-39879. https://doi.org/10.1609/aaai.v40i47.41394
Vancouver
Madmon O, Pipano I, Reinman I, Tennenholtz M. The Search for Stability: Learning Dynamics of Strategic Publishers with Initial Documents (Abstract Reprint). Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(47):39879-39879. doi:10.1609/aaai.v40i47.41394
BibTeX
@article{Madmon2026,
author = {Madmon, Omer and Pipano, Idan and Reinman, Itamar and Tennenholtz, Moshe},
title = {The Search for Stability: Learning Dynamics of Strategic Publishers with Initial Documents (Abstract Reprint)},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {47},
pages = {39879--39879},
doi = {10.1609/aaai.v40i47.41394}
}
EUVIMED