Web Agents Should Use Typed Actions Instead of Click-Based Browsing

2026-02-19 · Linxi Jiang, Rui Xi, Zhijie Liu, Shuo Chen, Zhiqiang Lin, Suman Nath arxiv

This position paper argues that building a reliable agentic Web requires shifting from low-level interaction primitives to typed actions supported by a semantic layer. Today's web agents primarily operate through clicks, keystrokes, and DOM manipulation, which leads to brittle long-horizon behavior, high execution cost, and limited auditability. We propose web verbs as a concrete design for this layer. A verb exposes a web operation as a typed function with structured inputs, structured outputs, and documented behavior, whether it is backed by a server-side Web API or a maintained client-side workflow. Verb calls can carry preconditions, postconditions, policy tags, and logging hooks, allowing agents to synthesize concise programs with explicit control flow and data flow and to produce checkable execution traces. Using representative case studies, we illustrate how verb-level composition can produce correct, reproducible outcomes, while browser agents using low-level interaction primitives may produce brittle behavior or incorrect reasoning. We conclude with a call to action on standardization, developer tooling, and community processes needed to make this semantic layer deployable and trustworthy at web scale.

📄 PDF Abstract BibTeX arXiv:2602.17245

Code (0)

등록된 구현이 없습니다.

Web Agents Should Adopt the Plan-Then-Execute Paradigm

2026-05-14 · Julien Piet, Annabella Chow, Yiwei Hou, Muxi Lyu 외 arxiv

ReAct has become the default architecture across LLM agents, and many existing web agents follow this paradigm. We argue that it is the wrong default for web agents. Instead, web agents should default to plan-then-execut…

PocketAgents: A Manifest-Driven Library of Autonomous Defense Agents

2026-05-20 · Sidnei Barbieri, Ágney Lopes Roth Ferraz, Lourenço Alves Pereira Júnior arxiv

Connecting large language models (LLMs) to defensive enforcement requires more than asking a model whether an attack is happening. A defender must decide which model outputs may change the system state, which outputs mus…

Strongly-Typed Agents are Guaranteed to Interact Safely

2017-02-24 · ICML 2017 8 · David Balduzzi

As artificial agents proliferate, it is becoming increasingly important to ensure that their interactions with one another are well-behaved. In this paper, we formalize a common-sense notion of when algorithms are well-b…

blind source separation Common Sense Reasoning Tensor Decomposition

Operating-Layer Controls for Onchain Language-Model Agents Under Real Capital

2026-04-28 · T. J. Barton, Chris Constantakis, Patti Hauseman, Annie Mous 외 arxiv

We study reliability in autonomous language-model agents that translate user mandates into validated tool actions under real capital. The setting is DX Terminal Pro, a 21-day deployment in which 3,505 user-funded agents …

VideoAgentTrek: Computer Use Pretraining from Unlabeled Videos

2025-10-22 · Dunjie Lu, Yiheng Xu, Junli Wang, Haoyuan Wu 외 arxiv

Training computer-use agents requires massive amounts of GUI interaction data, but manually annotating action trajectories at scale is prohibitively expensive. We present VideoAgentTrek, a scalable pipeline that automati…

Video Grounding