Metraipolis › archive › dc_7dec4b731860
Token Efficient Task Execution via Application Behavior Modeling for Web Agents — arXiv:2609.13491
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.13491
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T22:46:35.891Z
- SHA-256 of the archived text
81d73788592b4b9dd78de5bf742d3f8fe8f7979d882bbe437014f278bb5aeb92- Stable URL of this page
https://metraipolis.com/documento/dc_7dec4b731860
How to cite
Token Efficient Task Execution via Application Behavior Modeling for Web Agents — arXiv:2609.13491 — arXiv (en), https://arxiv.org/abs/2609.13491 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7dec4b731860 (Metraipolis archive dc_7dec4b731860, sha256 81d73788592b4b9dd78de5bf742d3f8fe8f7979d882bbe437014f278bb5aeb92)
BibTeX
@misc{dc7dec4b731860,
title = {Token Efficient Task Execution via Application Behavior Modeling for Web Agents — arXiv:2609.13491},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.13491},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7dec4b731860; sha256 81d73788592b4b9dd78de5bf742d3f8fe8f7979d882bbe437014f278bb5aeb92},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.13491. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
The strong performance of AI Agents across an impressive variety of tasks is driving an unprecedented investment in agentic infrastructures, however the cost of processing tokens is fast increasing. Web agents automate the execution of web-application tasks described in natural language, by analyzing the web-application's user interface (UI) and interacting with it. This work introduces OdoBot, a novel web-agent architecture that completes tasks at a fraction of the cost when compared to conventional web agents. This is achieved by leveraging a behavioral model of the underlying application constructed by analyzing successful task-execution demonstrations. Our experiments with 45 tasks on the Canvas Learning Management System (LMS) demonstrate that OdoBot uses 44% and 80% fewer tokens than two state-of-the-art competitor agents (Agent-E and WebVoyager), while also surpassing WebVoyager in terms of task success rate. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.13491 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-15T22:29:03.070Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).