Accessibility is crucial for inclusive usability of apps, however, developers often struggle to identify and fix app accessibility issues due to lack of knowledge, experience, and inadequate tools. Current accessibility testing tools can identify accessibility issues, but may not always provide guidance on how to address them. Introducing FixAlly, an automated tool designed to suggest source code fixes for accessibility issues detected by automated accessibility scanners. FixAlly employs a multi-agent LLM architecture to generate solution strategies, locate issues within the source code, and propose code modification suggestions to address the accessibility issue. Our empirical study demonstrates FixAlly's ability to suggest solutions that resolve issues found by accessibility scanners (with 77% effectiveness in generating plausible solution suggestions), and our survey of 12 iOS developers reveals that they would be willing to accept 69 .4% of the solution suggestions evaluated.
