Update README.md

README.md

@@ -172,11 +172,11 @@ We report results derived from the Agentless scaffold. Departing from the origin
 
 ### TAU-bench methodology 
 We evaluate TAU-Bench with the average passrate of 5 samples for each query, with GPT-4.1 as user model and without any custom tools. The maximum number of interaction steps is 40. 
-We prepend a general principle to the policy prompt.
-#### General
+Our general system prompt is: 
+```
 - In each round, you need to carefully examine the tools provided to you to determine if any can be used.
 - You must adhere to all of the policies. Pay attention to the details in the terms. Solutions for most situations can be found within these policies.
-
+``` 
 
 ## 3. Deployment Guide