Skip to content

h-akston/react_agent

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 

Repository files navigation

A light ReAct agent based on GPT-4o-mini

As part of my work for the Applied NLP course at the University of Arizona, I tested the effectiveness of 3 lightweight language models in common sense reasoning tasks by comparing 1-step and 2-step ReAct agents using GPT-4o mini and the TextWorldExpress Commonsense environment.

For this course project, I did conducted 50 episodes of testing, and the results demonstrate that the two-step ReAct agent achieves the highest performance, though scoring approximately 17% lower than similar agents using the full GPT-4 model. This suggests that lightweight models, when combined with appropriate prompting strategies, can offer a viable cost-efficient alternative in scenarios where moderate performance trade-offs are acceptable.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors