Vibeleaderboard
← All Intel
Intel / article

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

Source
arxiv.org
Author
Tu Nguyen, Duy Cao, Viet Nguyen, Phu Nguyen, Vy Le, Nguyen TK Nguyen, Tien N. Nguyen, Vu Nguyen
Date

Context

HxAgent plans web interactions one step at a time, checking the resulting page before choosing its next action. It combines the current page with memory of recent actions and lessons extracted from earlier successful or unsuccessful sequences. That gives the testing a way to revise its actions as the interface changes. Method.

The authors report 83.8% exact-match performance on a 350-task dataset. Here, exact match requires every action in a sequence to be correct. On the separate OnlineMind2Web , the reported score was 50.7%, showing how much the task setting matters. These measurements concern carrying out web interactions, rather than the proportion of application defects discovered. Evaluation and metric definitions.

Terms in this piece · Glossary
  • AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
  • eval — A repeatable test for AI quality — a set of tasks plus scoring — used the way software teams use test suites, because model output is too variable to judge by eyeballing.
  • LLM — A large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.
Recommended reads
Comments

Checking sign-in…

Loading comments…