English

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

Artificial Intelligence 2024-11-06 v2 Computation and Language

Abstract

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.

Keywords

Cite

@article{arxiv.2408.06458,
  title  = {Towards Autonomous Agents: Adaptive-planning, Reasoning, and Acting in Language Models},
  author = {Abhishek Dutta and Yen-Che Hsiao},
  journal= {arXiv preprint arXiv:2408.06458},
  year   = {2024}
}
R2 v1 2026-06-28T18:10:55.044Z