Adaptive Planning on the Web: Using LLMs and Affordances for Web Agents

Schmid SJ, Freund M, Harth A (2025)

Publication Type: Conference contribution

Publication year: 2025

Journal

Lecture Notes in Computer Science Springer Verlag

Publisher: Springer

Series: Lecture Notes in Computer Science

City/Town: Cham

Pages Range: 93-108

Conference Proceedings Title: Knowledge Graphs and Semantic Web

Event location: Paris FR

ISBN: 9783031812200

DOI: 10.1007/978-3-031-81221-7_7

Abstract

We investigate the adaption of agents using plans on the Web despite its large and dynamic nature, as well as agents’ constrained perception. Based on Semantic Web technologies and affordances, we compare how agents choose appropriate actions to adapt to their environment by condition-action rules or suggested actions of large language models. We conduct experiments on execution cost and plan stability distance to see whether agents choose appropriate actions to adapt their plans. We find that cost and stability of rule-based and LLMs for adaptation with affordances are close together, while performance differs greatly

Authors with CRIS profile

Sebastian Josef Schmid Lehrstuhl für Wirtschaftsinformatik, insbesondere Technische Informationssysteme Michael Freund
Andreas Harth Lehrstuhl für Wirtschaftsinformatik, insbesondere Technische Informationssysteme

Involved external institutions

Fraunhofer-Institut für Integrierte Schaltungen (IIS) DE Germany (DE)

How to cite

APA:

Schmid, S.J., Freund, M., & Harth, A. (2025). Adaptive Planning on the Web: Using LLMs and Affordances for Web Agents. In Knowledge Graphs and Semantic Web (pp. 93-108). Paris, FR: Cham: Springer.

MLA:

Schmid, Sebastian Josef, Michael Freund, and Andreas Harth. "Adaptive Planning on the Web: Using LLMs and Affordances for Web Agents." Proceedings of the 6th International Conference, KGSWC 2024, Paris Cham: Springer, 2025. 93-108.

BibTeX: Download