π The First Self-Improving agents with RL / Prompting Optimization
Python agentaigptmulti-agentpythonreinforcement-learningself-improvementsociety-of-mindswarm-intelligence
{
"agents": [
{
"name": "a general AI assistant",
"profile": "You are designed to answer questions.",
"strategy": "IO"
},
{
"name": "a general AI assistant number 2",
"profile": "You are designed to answer questions.",
"strategy": "ToT"
},
{
"name": "a general AI assistant number 3",
"profile": "You are designed to answer questions.",
"strategy": "ForwardPlanning"
}
]
}