Metacognition is all you need? Using Introspection in Generative Agents to Improve Goal-directed Behavior
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911786684383232 |
|---|---|
| author | Toy, Jason MacAdam, Josh Tabor, Phil |
| author_facet | Toy, Jason MacAdam, Josh Tabor, Phil |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_10910 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Metacognition is all you need? Using Introspection in Generative Agents to Improve Goal-directed Behavior Toy, Jason MacAdam, Josh Tabor, Phil Neurons and Cognition Artificial Intelligence 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. |
| title | Metacognition is all you need? Using Introspection in Generative Agents to Improve Goal-directed Behavior |
| topic | Neurons and Cognition Artificial Intelligence |
| url | https://arxiv.org/abs/2401.10910 |