Towards Autonomous Agents: Adaptive-planning, Reasoning, and Acting in Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Dutta, Abhishek, Hsiao, Yen-Che
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910684642541568
author Dutta, Abhishek
Hsiao, Yen-Che
author_facet Dutta, Abhishek
Hsiao, Yen-Che
contents We propose a novel in-context learning algorithm for building autonomous decision-making language agents. The language agent continuously attempts to solve the same task by self-correcting each time the task fails. Our selected language agent demonstrates the ability to solve tasks in a text-based game environment. Our results show that the gemma-2-9b-it language model, using our proposed method, can successfully complete two of six tasks that failed in the first attempt. This highlights the effectiveness of our approach in enhancing the problem-solving capabilities of a single language model through self-correction, paving the way for more advanced autonomous agents. The code is publicly available at https://github.com/YenCheHsiao/AutonomousLLMAgentwithAdaptingPlanning.
format Preprint
id arxiv_https___arxiv_org_abs_2408_06458
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Towards Autonomous Agents: Adaptive-planning, Reasoning, and Acting in Language Models
Dutta, Abhishek
Hsiao, Yen-Che
Artificial Intelligence
Computation and Language
We propose a novel in-context learning algorithm for building autonomous decision-making language agents. The language agent continuously attempts to solve the same task by self-correcting each time the task fails. Our selected language agent demonstrates the ability to solve tasks in a text-based game environment. Our results show that the gemma-2-9b-it language model, using our proposed method, can successfully complete two of six tasks that failed in the first attempt. This highlights the effectiveness of our approach in enhancing the problem-solving capabilities of a single language model through self-correction, paving the way for more advanced autonomous agents. The code is publicly available at https://github.com/YenCheHsiao/AutonomousLLMAgentwithAdaptingPlanning.
title Towards Autonomous Agents: Adaptive-planning, Reasoning, and Acting in Language Models
topic Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2408.06458