Building the Web for Agents: A Declarative Framework for Agent-Web Interaction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Schultze, Sven, Kietzmann, Meike Verena, Schönfeld, Nils-Lucas, Stock-Homburg, Ruth
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915618561720320
author Schultze, Sven
Kietzmann, Meike Verena
Schönfeld, Nils-Lucas
Stock-Homburg, Ruth
author_facet Schultze, Sven
Kietzmann, Meike Verena
Schönfeld, Nils-Lucas
Stock-Homburg, Ruth
contents The increasing deployment of autonomous AI agents on the web is hampered by a fundamental misalignment: agents must infer affordances from human-oriented user interfaces, leading to brittle, inefficient, and insecure interactions. To address this, we introduce VOIX, a web-native framework that enables websites to expose reliable, auditable, and privacy-preserving capabilities for AI agents through simple, declarative HTML elements. VOIX introduces <tool> and <context> tags, allowing developers to explicitly define available actions and relevant state, thereby creating a clear, machine-readable contract for agent behavior. This approach shifts control to the website developer while preserving user privacy by disconnecting the conversational interactions from the website. We evaluated the framework's practicality, learnability, and expressiveness in a three-day hackathon study with 16 developers. The results demonstrate that participants, regardless of prior experience, were able to rapidly build diverse and functional agent-enabled web applications. Ultimately, this work provides a foundational mechanism for realizing the Agentic Web, enabling a future of seamless and secure human-AI collaboration on the web.
format Preprint
id arxiv_https___arxiv_org_abs_2511_11287
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Building the Web for Agents: A Declarative Framework for Agent-Web Interaction
Schultze, Sven
Kietzmann, Meike Verena
Schönfeld, Nils-Lucas
Stock-Homburg, Ruth
Human-Computer Interaction
Artificial Intelligence
Computation and Language
Computers and Society
Multiagent Systems
H.5.2; I.2.11; I.2.7; H.3.5; K.4.1
The increasing deployment of autonomous AI agents on the web is hampered by a fundamental misalignment: agents must infer affordances from human-oriented user interfaces, leading to brittle, inefficient, and insecure interactions. To address this, we introduce VOIX, a web-native framework that enables websites to expose reliable, auditable, and privacy-preserving capabilities for AI agents through simple, declarative HTML elements. VOIX introduces <tool> and <context> tags, allowing developers to explicitly define available actions and relevant state, thereby creating a clear, machine-readable contract for agent behavior. This approach shifts control to the website developer while preserving user privacy by disconnecting the conversational interactions from the website. We evaluated the framework's practicality, learnability, and expressiveness in a three-day hackathon study with 16 developers. The results demonstrate that participants, regardless of prior experience, were able to rapidly build diverse and functional agent-enabled web applications. Ultimately, this work provides a foundational mechanism for realizing the Agentic Web, enabling a future of seamless and secure human-AI collaboration on the web.
title Building the Web for Agents: A Declarative Framework for Agent-Web Interaction
topic Human-Computer Interaction
Artificial Intelligence
Computation and Language
Computers and Society
Multiagent Systems
H.5.2; I.2.11; I.2.7; H.3.5; K.4.1
url https://arxiv.org/abs/2511.11287