HxAgent: Iterative Agent Planning for End-to-End Web Application Testing

ACL ARR 2026 January Submission4205 Authors

Keywords: Web UI Testing, Test Script Generation, Large Language Models

Abstract: In automated web testing, generating test cases and performing testing using functionality descriptions in natural-language is crucial for improving efficacy. These tasks require such a testing agent to carry out tasks on the target application and generating tests autonomously. We introduce HXAgent, an iterative LLM-based planning agent with a proactive correction strategy. After each step, HXAgent reassesses the web state to determine the next action using (1) current observations, (2) short-term memory of past actions, and (3) long-term experience extracted from past (in)correct sequences of actions. HXAgent achieves 97.4% Exact-Match accuracy on MiniWoB++, comparable to the best baselines without human demonstrations. On a dataset of 350 web tasks, it attains 83.8% Exact-Match and 91.8% Prefix-Match, surpassing baselines by 11.4%. On OnlineMind2Web, it further improves by 19.3%, demonstrating robust generalization.

Paper Type: Long

Research Area: AI/LLM Agents

Research Area Keywords: Autonomous agents,LLM agents,multi-modal agents,environment interaction

Contribution Types: NLP engineering experiment, Publicly available software and/or pre-trained models

Languages Studied: English

Submission Number: 4205