迈向自适应物理AI：LLM智能体能否管理长期物理任务？
原标题：Toward Self-Adaptive Physical AI: Can LLM Agents Manage Long-Horizon Physical Tasks?
AI 摘要
该研究探索LLM智能体能否以零样本方式自主管理长期物理任务并适应环境变化。作者设计了一个集成规划、工具调用、观察与验证的多智能体框架，并在农业任务上将其与强化学习智能体在不同天气模式下进行对比。结果显示，零样本LLM智能体在相同天气模式下可达到与RL相当的管理效果，且在环境变化时适应能力更强，为自适应物理AI智能体提供了可行路径。
正文节选
Toward Self-Adaptive Physical AI: Can LLM Agents Manage Long-Horizon Physical Tasks? Abstract Large Language Model (LLM) agents offer a promising path toward autonomously managing long-term physical tasks without human intervention. However, physical tasks require agents to continuously observe the environment, make consequential actions, and remain effective as the environment changes. Existing approaches either require substantial data and retraining, or primarily focus on agents operating in