具身系统中的生成式AI：性能、效率与可扩展性的系统级分析
Generative AI in Embodied Systems: System-Level Analysis of Performance, Efficiency and Scalability
AI总结：
本文首次对具身AI智能体进行系统级分析，将其划分为四种范式并开展基准测试，揭示了规划延迟、内存不一致等关键系统挑战，并提出了提升性能、效率和可扩展性的优化策略。
摘要：
具身系统通过由大语言模型（LLMs）驱动的集成感知、认知、动作和高级推理，使生成式自主智能体与物理世界交互，在真实世界环境中解决复杂、长时序、多目标任务方面具有巨大潜力。然而，由于运行时延迟过长、可扩展性有限和敏感性增强，导致严重的系统低效，部署这些系统仍具挑战性。本文旨在理解具身智能体系统的工作负载特征并探索优化方案。我们将这些系统系统地划分为四种范式，并进行基准测试研究，以评估它们在各种模块、智能体规模和具身任务上的任务性能和系统效率。我们的基准测试揭示了关键挑战，如规划和通信延迟过长、冗余的智能体交互、复杂的低级控制机制、内存不一致、提示词长度爆炸、对自我纠正和执行的敏感性、成功率急剧下降，以及随着智能体数量增加而降低的协作效率。利用这些性能分析洞察，我们提出了系统优化策略，以提高不同范式下具身智能体的性能、效率和可扩展性。本文首次对具身AI智能体进行系统级分析，并探索了推进未来具身系统设计的机会。
英文摘要：
Embodied systems, where generative autonomous agents engage with the physical world through integrated perception, cognition, action, and advanced reasoning powered by large language models (LLMs), hold immense potential for addressing complex, long-horizon, multi-objective tasks in real-world environments. However, deploying these systems remains challenging due to prolonged runtime latency, limited scalability, and heightened sensitivity, leading to significant system inefficiencies. In this paper, we aim to understand the workload characteristics of embodied agent systems and explore optimization solutions. We systematically categorize these systems into four paradigms and conduct benchmarking studies to evaluate their task performance and system efficiency across various modules, agent scales, and embodied tasks. Our benchmarking studies uncover critical challenges, such as prolonged planning and communication latency, redundant agent interactions, complex low-level control mechanisms, memory inconsistencies, exploding prompt lengths, sensitivity to self-correction and execution, sharp declines in success rates, and reduced collaboration efficiency as agent numbers increase. Leveraging these profiling insights, we suggest system optimization strategies to improve the performance, efficiency, and scalability of embodied agents across different paradigms. This paper presents the first system-level analysis of embodied AI agents, and explores opportunities for advancing future embodied system design.
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。
