Mengdi Chen

Research: Evaluate the performance using benchmarks

1

candidates - https://arxiv.org/abs/2402.05930 - https://arxiv.org/abs/2403.11905 Goals: - find a appropriate benchmark and understand the engineering workload to evaluate WebWand

Depended on #53 This would enable interesting workflows like "post a meme picture about workaholic in this slack chat" New tools like - get & save summary of page (news...

Support dropdown

1

We currently don’t support any kind of dropdown menu well

Currently, we query interactive elements using HTML semantics. There are some websites that do not always follow the rules. For example, I've seen this kind of button ``` New Job...

There are cases when the agent decides to type in an "input" on a page, but it turns out to be a fake one. For example, on expedia, this "Date"...

As of now WebWand doesn't scroll well when the scrollable portion is in part of the page (e.g. a dialog with long content) instead of the whole body of page...

We can try detect and add these information in prompt - agent tried to interactive with an element that does not exist - nothing visibly changed after last action (by...

https://developer.mozilla.org/en-US/docs/Mozilla/Add-ons/WebExtensions/API/find/find Would be useful on long pages when the task is about find certain information