Prune4Web: DOM Tree Pruning Programming for Web Agent
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (41) · 34710-34718
DOI: 10.1609/aaai.v40i41.40772 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Jiayuan Zhang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref).
Abstract (Originalsprache)
Web automation uses intelligent agents to perform high-level tasks by mimicking human interactions with webpages. Despite recent advances in LLM-based web agents, efficiently navigating complex, real-world webpages remains challenging due to massive DOM structures (10,000 ~ 100,000 tokens). Current approaches either truncate DOMs—losing vital information—or use inefficient heuristics and separate ranking models, failing to balance precision and scalability. We introduce Prune4Web, a novel paradigm that transforms DOM processing from LLM-based filtering to programmatic pruning. Our key innovation is DOM Tree Pruning Programming, where an LLM generates executable Python scoring programs to dynamically filter DOM elements based on semantic clues from decomposed sub-tasks. This approach eliminates the need for LLMs to process full DOMs, instead delegating traversal and scoring to lightweight, interpretable programs. The result is a 25 ~ 50 times reduction in candidate elements for grounding, enabling precise action localization without attention dilution. Additionally, we propose a data annotation method and a two-turn dialogue training strategy that jointly optimizes Planner, Programmatic Filter, and Grounder in a unified framework. Experiments demonstrate state-of-the-art performance. On our low-level task grounding task, our approach dramatically increases grounding accuracy from 46.80% to 88.28%, highlighting its effectiveness.
Zitieren
APA
Zhang, J., Chen, K., Lu, Z., Zhou, E., Yu, Q., & Zhang, J. (2026). Prune4Web: DOM Tree Pruning Programming for Web Agent. Proceedings of the AAAI Conference on Artificial Intelligence, 40(41), 34710-34718. https://doi.org/10.1609/aaai.v40i41.40772
Vancouver
Zhang J, Chen K, Lu Z, Zhou E, Yu Q, Zhang J. Prune4Web: DOM Tree Pruning Programming for Web Agent. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(41):34710-34718. doi:10.1609/aaai.v40i41.40772
BibTeX
@article{Zhang2026,
author = {Zhang, Jiayuan and Chen, Kaiquan and Lu, Zhihao and Zhou, Enshen and Yu, Qian and Zhang, Jing},
title = {Prune4Web: DOM Tree Pruning Programming for Web Agent},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {41},
pages = {34710--34718},
doi = {10.1609/aaai.v40i41.40772}
}
EUVIMED