| Full text | |
| Author(s): |
Cabrera, Eduardo Faria
;
de Barros, Marcel Rodrigues
;
Reali Costa, Anna Helena
Total Authors: 3
|
| Document type: | Journal article |
| Source: | INTELLIGENT SYSTEMS, BRACIS 2024, PT II; v. 15413, p. 15-pg., 2025-01-01. |
| Abstract | |
Large Language Models (LLMs) have shown remarkable capabilities across various applications but struggle with sequential decision-making tasks like planning. This work demonstrates that integrating LLMs with Finite-State Machines (FSMs) can enhance their reasoning and planning abilities, while also offering increased reliability. Several setup variants are compared, providing a better understanding of how validations, feedback loops, and restrictions enhance robustness and effectiveness. A comparison to the well known Chain-of-Thoughts approach is also provided. Our methods improve planning capabilities of all analysed LLMs, consistently increasing the success rate in solving tasks of varying complexities. A detailed analysis of the two best variants are provided, highlighting their respective strengths and weaknesses. (AU) | |
| FAPESP's process: | 19/07665-4 - Center for Artificial Intelligence |
| Grantee: | Fabio Gagliardi Cozman |
| Support Opportunities: | Research Grants - Research Program in eScience and Data Science - Research Centers in Engineering Program |