update readme and role-playing related code

README.md

@@ -2,55 +2,66 @@
 	🦉 OWL: Towards General Multi-Agent Assistant for Real-World Task Automation
 </h1>
 
-🦉 OWL is a cutting-edge framework for multi-agent collaboration that pushes the boundaries of task automation. 
-Built on top of the [Camel-AI Framework](https://github.com/camel-ai/camel). 
+🦉 OWL is a cutting-edge framework for multi-agent collaboration that pushes the boundaries of task automation, built on top of the [Camel-AI Framework](https://github.com/camel-ai/camel). 
 OWL ranks #1 among open-source frameworks on GAIA benchmark.
 
 Our vision is to revolutionize how AI agents collaborate to solve real-world tasks. By leveraging role-playing mechanisms and dynamic agent interactions, OWL enables more natural, efficient, and robust task automation across diverse domains.
 
 <!-- # Key Features -->
 
-# Quick Start
+# 🔥 News
 
-1. **Clone the Github repository:**
+
+# 🛠️ Installation
+
+## **Clone the Github repository:**
 
 ```bash
 $ git clone xxx
 ```
 
-2. **Set up Python Environment:**
+## **Set up Environment:**
 
 ```bash
 $ conda create -n owl python=3.11
 $ conda activate owl
 ```
 
-3. **Install Dependencies:**
+## **Install Dependencies:**
 
 ```bash
 $ pip install -r requirements.txt
 ```
 
-4. **Set API Keys:** We use `dotenv` to manage API keys. Please copy and check the `.env.example` file to `.env` and fill in the necessary API keys.
+##  **Set API Keys:** 
 
-5. **Run the Demo Code:**
+We use `dotenv` to manage API keys. Please copy and check the `.env.example` file to `.env` and fill in the necessary API keys.
+
+# 🚀 Quick Start
    
+Run the following minimal example:
+
 ```bash
 $ python run.py
 ```
 
-Additionally, We have provided a script to reproduce the results on GAIA. You can check the `run_gaia_roleplaying.py` file and run the following command:
+# 🧪 Experiments
+
+Additionally, We have provided a script to reproduce the results on GAIA. 
+You can check the `run_gaia_roleplaying.py` file and run the following command:
 
 ```bash
 $ python run_gaia_roleplaying.py
 ```
 
-# Community
-
-[Camel Link]
+# ⏱️ Future Plans
 
-[This project]
+- [ ] Write a technical blog post detailing our exploration and insights in multi-agent collaboration in real-world tasks.
+- [ ] Enhance the toolkit ecosystem with more specialized tools for domain-specific tasks.
+- [ ] Develop more sophisticated agent interaction patterns and communication protocols
 
 # Architecture
 
+
+
 # Cite

owl/run.py

@@ -8,14 +8,14 @@ from dotenv import load_dotenv
 from retry import retry
 from loguru import logger
 
-from utils import DeepSwarmRolePlaying, process_tools, run_society
+from utils import OwlRolePlaying, process_tools, run_society
 import os
 
 
 load_dotenv()
 
 
-def construct_society(question: str) -> DeepSwarmRolePlaying:
+def construct_society(question: str) -> OwlRolePlaying:
     r"""Construct the society based on the question."""
 
     user_role_name = "user"
@@ -62,7 +62,7 @@ def construct_society(question: str) -> DeepSwarmRolePlaying:
         'with_task_specify': False,
     }
 
-    society = DeepSwarmRolePlaying(
+    society = OwlRolePlaying(
         **task_kwargs,
         user_role_name=user_role_name,
         user_agent_kwargs=user_agent_kwargs,

owl/utils/enhanced_role_playing.py

@@ -22,7 +22,7 @@ from retry import retry
 from .common import *
 
 
-class DeepSwarmRolePlaying(RolePlaying):
+class OwlRolePlaying(RolePlaying):
     def __init__(
         self, 
         **kwargs
@@ -297,7 +297,7 @@ Please note that our overall task may be very complicated. Here are some tips th
         )
 
 
-class DeepSwarmGaiaRolePlaying(DeepSwarmRolePlaying):
+class OwlGaiaRolePlaying(OwlRolePlaying):
     def __init__(self, **kwargs):
         super().__init__(**kwargs)
 

owl/utils/gaia.py

@@ -217,7 +217,7 @@ class GAIABenchmark(BaseBenchmark):
                         'with_task_specify': False,
                     }
 
-                society = DeepSwarmGaiaRolePlaying(
+                society = OwlGaiaRolePlaying(
                     **task_kwargs,
                     user_role_name=user_role_name,
                     user_agent_kwargs=user_agent_kwargs,