Jiayi-Pan commited on
Commit
e46a3ef
·
verified ·
1 Parent(s): 9bc8b07

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -5
README.md CHANGED
@@ -6,17 +6,14 @@ colorTo: blue
6
  sdk: static
7
  pinned: false
8
  ---
 
9
 
10
  ### [Paper - Stay tuned for the Monday release!]() | [Project Page](https://berkeley-nlp.github.io/agent-eval-refine) | [Code](https://github.com/Berkeley-NLP/Agent-Eval-Refine)
11
 
12
- Model/Data associated with research project *Autonomous Evaluation and Refinement of Digital Agents*.
13
 
14
  TLDR: 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.
15
 
16
 
17
  [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/)
18
 
19
- UC Berkeley, University of Michigan
20
-
21
- ---
22
-
 
6
  sdk: static
7
  pinned: false
8
  ---
9
+ ## Model/Data associated with research project *Autonomous Evaluation and Refinement of Digital Agents*.
10
 
11
  ### [Paper - Stay tuned for the Monday release!]() | [Project Page](https://berkeley-nlp.github.io/agent-eval-refine) | [Code](https://github.com/Berkeley-NLP/Agent-Eval-Refine)
12
 
 
13
 
14
  TLDR: 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.
15
 
16
 
17
  [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/)
18
 
19
+ UC Berkeley, University of Michigan