Autonomous Intelligent Agents for Natural-Language-Driven Web Execution with Integrated Security Assurance

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Pasupuleti, Vinil, Bayyavarapu, Siva Rama Krishna Varma, Tyagi, Shrey
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916013761626112
author Pasupuleti, Vinil
Bayyavarapu, Siva Rama Krishna Varma
Tyagi, Shrey
author_facet Pasupuleti, Vinil
Bayyavarapu, Siva Rama Krishna Varma
Tyagi, Shrey
contents Modern web test suites rot. A UI refactor breaks locators, a timing change causes race conditions, and within weeks developers abandon the suite entirely. This paper presents an AI-driven autonomous testing framework that addresses these failure modes through five integrated strategies - navigation reliability, context-aware selector generation, post-generation validation, smart wait injection, and failure learning - implemented over a containerised worker architecture that decouples orchestration from long-running browser execution. Evaluated across four production applications and 176 scenarios, the framework improves script generation success from 55% to 93%, achieves an 8x reduction in navigation failures, eliminates 80% of timing-related race conditions, and reduces test creation time by 75% compared to manual Selenium authoring. The framework extends naturally to security validation: testers describe attack scenarios in plain English - "try accessing another user's invoice" - which the agent converts to OWASP Top 10-aligned browser probes, detecting 85% of authentication bypass vulnerabilities and 95% of input validation flaws with false positive rates below 12%. Natural-language-driven security testing of this kind represents, to our knowledge, a novel contribution to the field.
format Preprint
id arxiv_https___arxiv_org_abs_2605_15281
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Autonomous Intelligent Agents for Natural-Language-Driven Web Execution with Integrated Security Assurance
Pasupuleti, Vinil
Bayyavarapu, Siva Rama Krishna Varma
Tyagi, Shrey
Cryptography and Security
Artificial Intelligence
Modern web test suites rot. A UI refactor breaks locators, a timing change causes race conditions, and within weeks developers abandon the suite entirely. This paper presents an AI-driven autonomous testing framework that addresses these failure modes through five integrated strategies - navigation reliability, context-aware selector generation, post-generation validation, smart wait injection, and failure learning - implemented over a containerised worker architecture that decouples orchestration from long-running browser execution. Evaluated across four production applications and 176 scenarios, the framework improves script generation success from 55% to 93%, achieves an 8x reduction in navigation failures, eliminates 80% of timing-related race conditions, and reduces test creation time by 75% compared to manual Selenium authoring. The framework extends naturally to security validation: testers describe attack scenarios in plain English - "try accessing another user's invoice" - which the agent converts to OWASP Top 10-aligned browser probes, detecting 85% of authentication bypass vulnerabilities and 95% of input validation flaws with false positive rates below 12%. Natural-language-driven security testing of this kind represents, to our knowledge, a novel contribution to the field.
title Autonomous Intelligent Agents for Natural-Language-Driven Web Execution with Integrated Security Assurance
topic Cryptography and Security
Artificial Intelligence
url https://arxiv.org/abs/2605.15281