MSI-Agent: Incorporating Multi-Scale Insight into Embodied Agents for Superior Planning and Decision-Making
This addresses the challenge of effective insight utilization for embodied agents, though it appears incremental as it builds on existing insight strategies.
The paper tackles the problem of irrelevant and insufficient insights in long-term memory for embodied agents by introducing MSI-Agent, which uses a multi-scale approach to generate and select insights, resulting in improved planning performance over another insight strategy with GPT3.5 and better robustness in domain-shifting scenarios.
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.