Metacognition is all you need? Using Introspection in Generative Agents to Improve Goal-directed Behavior
This addresses challenges in generative agents for AI applications, though it appears incremental as it builds on existing cognitive process frameworks.
The paper tackles the problem of LLMs' limited context windows and generalization difficulties by introducing a metacognition module that enables generative agents to observe their own thought processes and actions, resulting in significantly enhanced performance and strategy adaptation in scenarios like a zombie apocalypse.
Recent advances in Large Language Models (LLMs) have shown impressive capabilities in various applications, yet LLMs face challenges such as limited context windows and difficulties in generalization. In this paper, we introduce a metacognition module for generative agents, enabling them to observe their own thought processes and actions. This metacognitive approach, designed to emulate System 1 and System 2 cognitive processes, allows agents to significantly enhance their performance by modifying their strategy. We tested the metacognition module on a variety of scenarios, including a situation where generative agents must survive a zombie apocalypse, and observe that our system outperform others, while agents adapt and improve their strategies to complete tasks over time.