# LiteWebAgent: The Open-Source Suite for VLM-Based Web-Agent Applications

Source: [LiteWebAgent: The Open-Source Suite for VLM-Based Web-Agent Applications](<https://www.sota2.com/research/paper/68fa78691e209131cea784b1>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:57:16.117Z

Authors: Danqing Zhang, Balaji Rama, Jingyi Ni, Shiying He, Fu Zhao, Kunyu Chen, Arnold Chen, Junyu Cao

Published: 2025-03-04T19:13:10.000Z

## Abstract

We introduce LiteWebAgent, an open-source suite for VLM-based web agent applications. Our framework addresses a critical gap in the web agent ecosystem with a production-ready solution that combines minimal serverless backend configuration, intuitive user and browser interfaces, and extensible research capabilities in agent planning, memory, and tree search. For the core LiteWebAgent agent framework, we implemented a simple yet effective baseline using recursive function calling, providing with decoupled action generation and action grounding. In addition, we integrate advanced research components such as agent planning, agent workflow memory, and tree search in a modular and extensible manner. We then integrate the LiteWebAgent agent framework with frontend and backend as deployed systems in two formats: (1) a production Vercel-based web application, which provides users with an agent-controlled remote browser, (2) a Chrome extension leveraging LiteWebAgent's API to control an existing Chrome browser via CDP (Chrome DevTools Protocol). The LiteWebAgent framework is available at https://github.com/PathOnAI/LiteWebAgent, with deployed frontend at https://lite-web-agent.vercel.app/.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Web Agent Attack Success Rate on AGENTBAIT Evaluation Suite](<https://www.sota2.com/research/sota/web-agent-attack-success-rate-on-agentbait-evaluation-suite.md>): Web Agent Attack Success Rate; AGENTBAIT Evaluation Suite; ASR: 87.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2503.02950>)

[PDF](<https://arxiv.org/pdf/2503.02950.pdf>)
