ITCMA:一种基于计算意识结构的生成式智能体
ITCMA: A Generative Agent Based on a Computational Consciousness Structure
AI总结:
本文提出基于内部时间意识机(ITCM)的智能体 ITCMA,通过模拟人类意识过程增强大语言模型对隐含指令和常识的理解,在 Alfworld 和四足机器人任务中均取得优于 SOTA 的完成率与泛化能力。
摘要:
大语言模型(LLMs)在需要理解隐含指令和应用常识知识的任务中仍面临挑战。在此类场景下,LLMs 可能需要多次尝试才能达到人类水平的表现,这在实际环境中可能导致不准确的响应或推理,进而影响其长期一致性和行为。本文引入了内部时间意识机(ITCM),这是一种用于模拟人类意识过程的计算意识结构。我们进一步提出了基于 ITCM 的智能体(ITCMA),它支持在开放世界环境中进行动作生成和推理,并能够独立完成任务。ITCMA 通过考虑智能体与环境的交互和推理,增强了 LLMs 理解隐含指令和应用常识知识的能力。在 Alfworld 环境中的评估表明,经过训练的 ITCMA 在已见集合上的表现比当前最优方法(SOTA)高出 9%。即使未经训练的 ITCMA 在已见集合上也实现了 96% 的任务完成率,比 SOTA 高 5%,这表明其在效用性和泛化性方面优于传统智能体。在四足机器人的真实世界任务中,未经训练的 ITCMA 实现了 85% 的任务完成率,接近其在未见集合上的表现,证明了其在真实世界环境中具有可比的效用性和普适性。
英文摘要:
Large Language Models (LLMs) still face challenges in tasks requiring understanding implicit instructions and applying common-sense knowledge. In such scenarios, LLMs may require multiple attempts to achieve human-level performance, potentially leading to inaccurate responses or inferences in practical environments, affecting their long-term consistency and behavior. This paper introduces the Internal Time-Consciousness Machine (ITCM), a computational consciousness structure to simulate the process of human consciousness. We further propose the ITCM-based Agent (ITCMA), which supports action generation and reasoning in open-world settings, and can independently complete tasks. ITCMA enhances LLMs' ability to understand implicit instructions and apply common-sense knowledge by considering agents' interaction and reasoning with the environment. Evaluations in the Alfworld environment show that trained ITCMA outperforms the state-of-the-art (SOTA) by 9% on the seen set. Even untrained ITCMA achieves a 96% task completion rate on the seen set, 5% higher than SOTA, indicating its superiority over traditional intelligent agents in utility and generalization. In real-world tasks with quadruped robots, the untrained ITCMA achieves an 85% task completion rate, which is close to its performance in the unseen set, demonstrating its comparable utility and universality in real-world settings.
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。