arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.06458cs.AIcs.CL
收藏

迈向自主智能体:语言模型中的自适应规划、推理与行动

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

University of Connecticut(康涅狄格大学)

Abhishek Dutta, Yen-Che Hsiao

AI总结:

提出一种基于上下文学习的自适应规划算法,使语言智能体通过自我纠正反复尝试任务,在文本游戏中成功完成六项任务中的两项,增强了单模型的问题解决能力。

摘要:

我们提出了一种新颖的上下文学习算法,用于构建自主决策语言智能体。该语言智能体通过每次任务失败时进行自我纠正,持续尝试解决同一任务。我们所选的语言智能体展示了在基于文本的游戏环境中解决任务的能力。我们的结果表明,使用我们提出的方法,gemma-2-9b-it语言模型能够成功完成六项任务中的两项,而这些任务在首次尝试时均告失败。这凸显了我们的方法通过自我纠正增强单个语言模型问题解决能力的有效性,为更先进的自主智能体铺平了道路。代码可在 https://github.com/YenCheHsiao/AutonomousLLMAgentwithAdaptingPlanning 公开获取。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑