Update README.md

README.md

@@ -11,7 +11,7 @@ pinned: false
 ### [Paper - Stay tuned for the Tuesday release!]() | [Code](https://github.com/Berkeley-NLP/Agent-Eval-Refine)
 
 
-We explore the design and use of model-based evaluators to both evaluate and autonomously refine the performance of digital agents. Experiments show that domain-general automated evaluators can significantly improve the performance of digital agents, without any extra supervision.
+We design and use model-based evaluators to both evaluate and autonomously refine the performance of digital agents. Experiments show that domain-general automated evaluators can significantly improve the performance of digital agents, without any extra supervision.
 
 
 [Jiayi Pan](https://www.jiayipan.me/), [Yichi Zhang](https://sled.eecs.umich.edu/author/yichi-zhang/), [Nicholas Tomlin](https://people.eecs.berkeley.edu/~nicholas_tomlin/), [Yifei Zhou](https://yifeizhou02.github.io/), [Sergey Levine](https://people.eecs.berkeley.edu/~svlevine/), [Alane Suhr](https://www.alanesuhr.com/)