LLM Powered Autonomous Agents

Lilian Weng · 3 years ago

Large language models are being developed as the core controllers of autonomous agent systems that can break down complex tasks into subgoals, maintain both short and long-term memory, and call external tools and APIs. Examples include AutoGPT, GPT-Engineer, and BabyAGI, which demonstrate how LLMs can function as general problem solvers beyond text generation. These agent systems enable improved task completion through planning, reflection, memory retention, and access to information beyond the model's original training data.