AgentRank: Trajectory-Aware Document Ranking for Autonomous Information Retrieval
ACM AI Letters · 2026
DOI: 10.1145/3828671 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM AI Letters, 2026. Verfasst von Daniel Schall. Die Arbeit nennt 17 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Traditional information retrieval systems rank documents by semantic similarity, yet this fails to capture document utility for autonomous agents in multi-step tasks. We introduce AgentRank, a ranking framework that learns from agent execution trajectories to identify documents leading to task completion. Using dual PageRank on success/failure trajectory graphs, Thompson Sampling, and terminal path analysis, AgentRank reduces semantic dead-ends by 79% compared to the strongest baseline (LinUCB contextual bandit) while maintaining perfect task completion rates in our controlled evaluation. Ablation analysis identifies terminal path bonus as the most critical component, and sensitivity analysis characterizes the operating regime where trajectory learning provides significant benefit.
Zitieren
APA
Schall, D. (2026). AgentRank: Trajectory-Aware Document Ranking for Autonomous Information Retrieval. ACM AI Letters. https://doi.org/10.1145/3828671
Vancouver
Schall D. AgentRank: Trajectory-Aware Document Ranking for Autonomous Information Retrieval. ACM AI Letters. 2026. doi:10.1145/3828671
BibTeX
@article{Schall2026,
author = {Schall, Daniel},
title = {AgentRank: Trajectory-Aware Document Ranking for Autonomous Information Retrieval},
journal = {ACM AI Letters},
year = {2026},
doi = {10.1145/3828671}
}
EUVIMED