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. We further propose the ITCM-based Agent (ITCMA), which supports behavior generation and reasoning in open-world settings. 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 in real-world settings.

翻译：大语言模型（LLMs）在涉及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性能，这可能导致在实际环境中产生不准确的响应或推理，进而影响其长期一致性和行为。本文提出内部时间意识机器（ITCM），一种计算意识结构。我们进一步提出基于ITCM的智能体（ITCMA），支持开放世界环境中的行为生成与推理。ITCMA通过考虑智能体与环境之间的交互与推理，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在可见测试集上以9%的优势超越现有最先进方法（SOTA）。即使未经训练的ITCMA在可见测试集上也能达到96%的任务完成率，较SOTA高出5%，凸显其在效用性和泛化性方面优于传统智能体。在与四足机器人结合的真实世界任务中，未经训练的ITCMA实现了85%的任务完成率，与其在未见测试集上的表现相近，证明了其在真实场景中具有相当的实用性。