MSI-Agent：将多尺度洞察力融入具身体性的智能体，以实现更优越的规划和决策

MSI-Agent: Incorporating Multi-Scale Insight into Embodied Agents for Superior Planning and Decision-Making

September 25, 2024

作者: Dayuan Fu, Biqing Qi, Yihuai Gao, Che Jiang, Guanting Dong, Bowen Zhou

cs.AI

摘要

长期记忆对于代理人非常重要，其中洞察力发挥着关键作用。然而，不相关洞察的出现和缺乏通用洞察可能会严重削弱洞察的有效性。为了解决这个问题，在本文中，我们介绍了多尺度洞察代理（MSI-Agent），这是一个具有实体的代理人，旨在通过有效地总结和利用不同尺度上的洞察，提高LLMs的规划和决策能力。MSI通过经验选择器、洞察生成器和洞察选择器实现这一目标。利用三部分流程，MSI可以生成特定任务的高层洞察，将其存储在数据库中，然后利用其中的相关洞察来辅助决策。我们的实验表明，与另一种洞察策略相比，MSI在通过GPT3.5进行规划时表现更好。此外，我们深入探讨了选择种子经验和洞察的策略，旨在为LLM提供更有用和相关的洞察，以实现更好的决策。我们的观察还表明，MSI在面对领域转移情景时表现出更好的鲁棒性。

English

Long-term memory is significant for agents, in which insights play a crucial role. However, the emergence of irrelevant insight and the lack of general insight can greatly undermine the effectiveness of insight. To solve this problem, in this paper, we introduce Multi-Scale Insight Agent (MSI-Agent), an embodied agent designed to improve LLMs' planning and decision-making ability by summarizing and utilizing insight effectively across different scales. MSI achieves this through the experience selector, insight generator, and insight selector. Leveraging a three-part pipeline, MSI can generate task-specific and high-level insight, store it in a database, and then use relevant insight from it to aid in decision-making. Our experiments show that MSI outperforms another insight strategy when planning by GPT3.5. Moreover, We delve into the strategies for selecting seed experience and insight, aiming to provide LLM with more useful and relevant insight for better decision-making. Our observations also indicate that MSI exhibits better robustness when facing domain-shifting scenarios.