Guardado en:
Detalles Bibliográficos
Autores principales: Borchmann, Łukasz, Van Landeghem, Jordy, Turski, Michał, Padarha, Shreyansh, Kearns, Ryan Othniel, Mahdi, Adam, Rogge, Niels, Fourrier, Clémentine, Han, Siwei, Yao, Huaxiu, Llabrés, Artemis, Xu, Yiming, Karatzas, Dimosthenis, Zhang, Hao, Datta, Anupam
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2603.12180
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866918399700893696
author Borchmann, Łukasz
Van Landeghem, Jordy
Turski, Michał
Padarha, Shreyansh
Kearns, Ryan Othniel
Mahdi, Adam
Rogge, Niels
Fourrier, Clémentine
Han, Siwei
Yao, Huaxiu
Llabrés, Artemis
Xu, Yiming
Karatzas, Dimosthenis
Zhang, Hao
Datta, Anupam
author_facet Borchmann, Łukasz
Van Landeghem, Jordy
Turski, Michał
Padarha, Shreyansh
Kearns, Ryan Othniel
Mahdi, Adam
Rogge, Niels
Fourrier, Clémentine
Han, Siwei
Yao, Huaxiu
Llabrés, Artemis
Xu, Yiming
Karatzas, Dimosthenis
Zhang, Hao
Datta, Anupam
contents Multimodal agents offer a promising path to automating complex document-intensive workflows. Yet, a critical question remains: do these agents demonstrate genuine strategic reasoning, or merely stochastic trial-and-error search? To address this, we introduce MADQA, a benchmark of 2,250 human-authored questions grounded in 800 heterogeneous PDF documents. Guided by Classical Test Theory, we design it to maximize discriminative power across varying levels of agentic abilities. To evaluate agentic behaviour, we introduce a novel evaluation protocol measuring the accuracy-effort trade-off. Using this framework, we show that while the best agents can match human searchers in raw accuracy, they succeed on largely different questions and rely on brute-force search to compensate for weak strategic planning. They fail to close the nearly 20% gap to oracle performance, persisting in unproductive loops. We release the dataset and evaluation harness to help facilitate the transition from brute-force retrieval to calibrated, efficient reasoning.
format Preprint
id arxiv_https___arxiv_org_abs_2603_12180
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Strategic Navigation or Stochastic Search? How Agents and Humans Reason Over Document Collections
Borchmann, Łukasz
Van Landeghem, Jordy
Turski, Michał
Padarha, Shreyansh
Kearns, Ryan Othniel
Mahdi, Adam
Rogge, Niels
Fourrier, Clémentine
Han, Siwei
Yao, Huaxiu
Llabrés, Artemis
Xu, Yiming
Karatzas, Dimosthenis
Zhang, Hao
Datta, Anupam
Computation and Language
Artificial Intelligence
Multimodal agents offer a promising path to automating complex document-intensive workflows. Yet, a critical question remains: do these agents demonstrate genuine strategic reasoning, or merely stochastic trial-and-error search? To address this, we introduce MADQA, a benchmark of 2,250 human-authored questions grounded in 800 heterogeneous PDF documents. Guided by Classical Test Theory, we design it to maximize discriminative power across varying levels of agentic abilities. To evaluate agentic behaviour, we introduce a novel evaluation protocol measuring the accuracy-effort trade-off. Using this framework, we show that while the best agents can match human searchers in raw accuracy, they succeed on largely different questions and rely on brute-force search to compensate for weak strategic planning. They fail to close the nearly 20% gap to oracle performance, persisting in unproductive loops. We release the dataset and evaluation harness to help facilitate the transition from brute-force retrieval to calibrated, efficient reasoning.
title Strategic Navigation or Stochastic Search? How Agents and Humans Reason Over Document Collections
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2603.12180