Research

Paper

AI LLM February 19, 2026

Web Verbs: Typed Abstractions for Reliable Task Composition on the Agentic Web

Authors

Linxi Jiang, Rui Xi, Zhijie Liu, Shuo Chen, Zhiqiang Lin, Suman Nath

Abstract

The Web is evolving from a medium that humans browse to an environment where software agents act on behalf of users. Advances in large language models (LLMs) make natural language a practical interface for goal-directed tasks, yet most current web agents operate on low-level primitives such as clicks and keystrokes. These operations are brittle, inefficient, and difficult to verify. Complementing content-oriented efforts such as NLWeb's semantic layer for retrieval, we argue that the agentic web also requires a semantic layer for web actions. We propose \textbf{Web Verbs}, a web-scale set of typed, semantically documented functions that expose site capabilities through a uniform interface, whether implemented through APIs or robust client-side workflows. These verbs serve as stable and composable units that agents can discover, select, and synthesize into concise programs. This abstraction unifies API-based and browser-based paradigms, enabling LLMs to synthesize reliable and auditable workflows with explicit control and data flow. Verbs can carry preconditions, postconditions, policy tags, and logging support, which improves \textbf{reliability} by providing stable interfaces, \textbf{efficiency} by reducing dozens of steps into a few function calls, and \textbf{verifiability} through typed contracts and checkable traces. We present our vision, a proof-of-concept implementation, and representative case studies that demonstrate concise and robust execution compared to existing agents. Finally, we outline a roadmap for standardization to make verbs deployable and trustworthy at web scale.

Metadata

arXiv ID: 2602.17245
Provider: ARXIV
Primary Category: cs.AI
Published: 2026-02-19
Fetched: 2026-02-21 18:51

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2602.17245v1</id>\n    <title>Web Verbs: Typed Abstractions for Reliable Task Composition on the Agentic Web</title>\n    <updated>2026-02-19T10:50:52Z</updated>\n    <link href='https://arxiv.org/abs/2602.17245v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2602.17245v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>The Web is evolving from a medium that humans browse to an environment where software agents act on behalf of users. Advances in large language models (LLMs) make natural language a practical interface for goal-directed tasks, yet most current web agents operate on low-level primitives such as clicks and keystrokes. These operations are brittle, inefficient, and difficult to verify. Complementing content-oriented efforts such as NLWeb's semantic layer for retrieval, we argue that the agentic web also requires a semantic layer for web actions. We propose \\textbf{Web Verbs}, a web-scale set of typed, semantically documented functions that expose site capabilities through a uniform interface, whether implemented through APIs or robust client-side workflows. These verbs serve as stable and composable units that agents can discover, select, and synthesize into concise programs. This abstraction unifies API-based and browser-based paradigms, enabling LLMs to synthesize reliable and auditable workflows with explicit control and data flow. Verbs can carry preconditions, postconditions, policy tags, and logging support, which improves \\textbf{reliability} by providing stable interfaces, \\textbf{efficiency} by reducing dozens of steps into a few function calls, and \\textbf{verifiability} through typed contracts and checkable traces. We present our vision, a proof-of-concept implementation, and representative case studies that demonstrate concise and robust execution compared to existing agents. Finally, we outline a roadmap for standardization to make verbs deployable and trustworthy at web scale.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <published>2026-02-19T10:50:52Z</published>\n    <arxiv:primary_category term='cs.AI'/>\n    <author>\n      <name>Linxi Jiang</name>\n    </author>\n    <author>\n      <name>Rui Xi</name>\n    </author>\n    <author>\n      <name>Zhijie Liu</name>\n    </author>\n    <author>\n      <name>Shuo Chen</name>\n    </author>\n    <author>\n      <name>Zhiqiang Lin</name>\n    </author>\n    <author>\n      <name>Suman Nath</name>\n    </author>\n  </entry>"
}