AutoAgents is an open source LLM-based automatic agent generation experimental application. This program is driven by LLM and can automatically generate multi-role agents based on the goals you set. It can determine the expert roles that need to be added and the specific execution plan based on the problem. Contains agent generator, execution plan generator, result reflection module, etc. LLM is made like a human being who can autonomously assign different roles according to the problem, formulate and execute a plan to solve the problem.
Demand group:
"Can be used to explore the multi-role collaboration potential of LLM and build more intelligent conversational robots"
Example of usage scenario:
LLM can be used to generate roles such as doctors, patients, and pharmacists to collaborate to solve a health problem.
LLM can be used to generate roles such as teachers, students, and parents to collaborate on a teaching task.
LLM can be used to generate characters such as detectives, police officers, and lawyers to collaborate on solving an unsolved crime.
Product features:
Agent generation
Execution plan generation
Reflection on results