从LLM到现成智能体的具身思维链蒸馏
Embodied CoT Distillation From LLM To Off-the-shelf Agents
AI总结：
DeDer框架通过将LLM的具身推理分解为推理与规划策略并蒸馏至小语言模型，在ALFRED基准上超越现有方法，实现现成设备上的高效具身决策。
摘要：
我们解决了在决策系统需在容量受限的现成设备上及时运行的场景中，利用大型语言模型（LLM）处理复杂具身任务的挑战。我们提出了DeDer，一个将LLM的具身推理能力分解并蒸馏为高效的小语言模型（sLM）策略的框架。在DeDer中，基于LLM的策略决策过程被重构为包含推理策略和规划策略的层次结构。推理策略是从LLM的具身上下文学习和自我验证生成的数据中蒸馏而来，因此它能产生有效的理由。规划策略在理由的引导下，能高效地生成优化计划。反过来，DeDer允许采用sLM作为这两种策略，并部署在现成设备上。此外，为了增强针对具身任务的中间理由的质量，我们设计了具身知识图谱，并且为了通过单次推理及时生成多个理由，我们还使用了对比提示的注意力模型。我们在ALFRED基准上的实验表明，DeDer超越了领先的语言规划和蒸馏方法，证明了通过DeDer得到的基于sLM的具身策略的适用性和效率。
英文摘要：
We address the challenge of utilizing large language models (LLMs) for complex embodied tasks, in the environment where decision-making systems operate timely on capacity-limited, off-the-shelf devices. We present DeDer, a framework for decomposing and distilling the embodied reasoning capabilities from LLMs to efficient, small language model (sLM)-based policies. In DeDer, the decision-making process of LLM-based strategies is restructured into a hierarchy with a reasoning-policy and planning-policy. The reasoning-policy is distilled from the data that is generated through the embodied in-context learning and self-verification of an LLM, so it can produce effective rationales. The planning-policy, guided by the rationales, can render optimized plans efficiently. In turn, DeDer allows for adopting sLMs for both policies, deployed on off-the-shelf devices. Furthermore, to enhance the quality of intermediate rationales, specific to embodied tasks, we devise the embodied knowledge graph, and to generate multiple rationales timely through a single inference, we also use the contrastively prompted attention model. Our experiments with the ALFRED benchmark demonstrate that DeDer surpasses leading language planning and distillation approaches, indicating the applicability and efficiency of sLM-based embodied policies derived through DeDer.
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。
