search-agents

search-agents copied to clipboard

image is broken

1

this image, `jykoh/classifieds`, is broken ```bash Using default tag: latest latest: Pulling from jykoh/classifieds af107e978371: Already exists 6480d4ad61d2: Pull complete 95f5176ece8b: Pull complete 0ebe7ec824ca: Pull complete 2330b2e5ceb7: Pull complete 630356341a53:...

Mai0313

How many times is the value function evaluated in the your " VisualWebArena benchmark" experiment?

1

 I found if I just run the scripts to test "VisualWebArena benchmark" experiment. The task finnally will fail in many times. Did you set just one model in models?...

870572761

Value function for Text WebArena is multi-modal

6

Thanks for sharing the interesting work! I notice that the script to run the text WebArena evaluation utilizes the value function here https://github.com/kohjingyu/search-agents/blob/c14a5d1bf2bea07f7aaa761d460c9d44e953d95f/agent/value_function.py#L16 which is by default multi-modal. I think...

Olafyii