Towards Autonomous Agents: Adaptive-planning, Reasoning, and Acting in Language Models
This work addresses the challenge of enhancing problem-solving capabilities in language models for autonomous agents, though it appears incremental with limited task scope.
The paper tackles the problem of building autonomous decision-making language agents by proposing a novel in-context learning algorithm that enables self-correction when tasks fail, resulting in the gemma-2-9b-it model successfully completing two of six previously failed tasks.
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.