{% extends 'bootstrap_base.html' %} {% from 'bootstrap5/form.html' import render_field %} {% block header %}

Stage II: Execution

In the execution stage, the plan will be used to instruct large language models to choose actions to execute. In each step, you will see the assistant predicted action. After finishing the whole plan, you can continue to next task.

{% endblock %} {% block content %}

After you click button 'start'. The execution process will be presented in a conversation. We provide one screenshot of our conversational interface below to show you the options:

Response to Action Prediction

The plan will be executed step-by-step with transforming each primary step into one action. After one action is predicted, you can choose from the three options:


Responsive image

How to address potential errors

However, the LLM assistants may also make errors. The potential cases for action prediction are:


The action specification includes two-stages: (1) select one action (2) fill in action parameters. Their screenshots are shown below:

Responsive image Responsive image

After Execution of one Step

After one action is executed, you can choose:

After all steps are executed, the submit button will be displayed, and then you can move to next task.


Responsive image
{% endblock %}