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

TL;DR

This paper introduces Web Verbs, a typed, semantic abstraction layer for web actions that enhances the reliability, efficiency, and verifiability of goal-directed web agents by unifying API and browser-based interactions.

Contribution

It proposes Web Verbs as a standardized, semantic set of web actions that enable more reliable, efficient, and verifiable web automation for agents, bridging API and browser paradigms.

Findings

Web Verbs improve agent reliability and robustness.

The approach reduces complex workflows into concise function calls.

Case studies demonstrate enhanced execution compared to existing agents.

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.