Toward Self-Adaptive Physical AI: Can LLM Agents Manage Long-Horizon Physical Tasks?

A multi-agent framework integrating planning, tool calling, observation, and verification lets zero-shot LLM agents match reinforcement learning agents on long-horizon agricultural management tasks under the same weather pattern and adapt more effectively than RL agents when the environment shifts, according to arXiv paper 2609.13436v1. The authors report the results as evidence for a path toward self-adaptive physical AI agents that manage long-term physical tasks without human intervention or retraining.

arXiv:2609.13436v1 Announce Type: new 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 the virtual world. In this work, we explore the feasibility of building a self-adaptive physical AI agent that manages long-term physical tasks in a zero-shot manner and adapts to environmental changes without human intervention. We design a multi-agent framework that integrates planning, tool calling, observation, and verification, and evaluate it on agricultural tasks against reinforcement learning RL agents under different weather patterns. Our results show that zero-shot LLM agents can achieve comparable management outcomes to RL agents under the same weather pattern and adapt more effectively than RL when evaluated under a shifted environment, highlighting a promising path toward self-adaptive physical AI agents.