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

• URL: http://arxiv.org/abs/2609.13436v1
• Date: Fri, 11 Sep 2026 18:52:40 GMT
• Title: Toward Self-Adaptive Physical AI: Can LLM Agents Manage Long-Horizon Physical Tasks?
• Abstract summary: Large Language Model (LLM) agents offer a promising path toward autonomously managing long-term physical tasks without human intervention.<n>Existing approaches either require substantial data and retraining, or primarily focus on agents operating in the virtual world.<n>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.
• Score: 1.6822770693792826
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• State2State: Environment-Derived Mid-Training for LLM Agents [67.08889234341996]
  We study an environment learning paradigm in which agents acquire interaction and manipulation capabilities solely through environment interaction.<n>We propose State2State, an environment-derived mid-training method that converts explored environment states into training objectives.<n> Experiments on ALFWorld and ScienceWorld show that State2State improves agent performance as a standalone environment-learning stage in most settings.
  arXiv  Detail & Related papers  (2026-08-05T15:02:41Z)
• Role-Agent: Bootstrapping LLM Agents via Dual-Role Evolution [25.26084224278813]
  Role-Agent harnesses a single Large Language Model (LLM) to function concurrently as both the agent and the environment.<n>Role-Agent consistently improves performance, yielding an average gain of over 4% over strong baselines.
  arXiv  Detail & Related papers  (2026-06-09T14:28:07Z)
• Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence [122.8626256816085]
  textbfAgent-World is a self-evolving training arena for advancing general agent intelligence through scalable environments.<n>Agent-World-8B and 14B consistently outperforms strong proprietary models and environment scaling baselines.
  arXiv  Detail & Related papers  (2026-04-20T14:01:10Z)
• Autonomous Continual Learning of Computer-Use Agents for Environment Adaptation [57.65688895630163]
  We introduce ACuRL, an Autonomous Curriculum Reinforcement Learning framework that continually adapts agents to specific environments with zero human data.<n>Our method effectively enables both intra-environment and cross-environment continual learning, yielding 4-22% performance gains without forgetting existing environments.
  arXiv  Detail & Related papers  (2026-02-10T23:06:02Z)
• Scaling Autonomous Agents via Automatic Reward Modeling And Planning [52.39395405893965]
  Large language models (LLMs) have demonstrated remarkable capabilities across a range of tasks.<n>However, they still struggle with problems requiring multi-step decision-making and environmental feedback.<n>We propose a framework that can automatically learn a reward model from the environment without human annotations.
  arXiv  Detail & Related papers  (2025-02-17T18:49:25Z)
• Gödel Agent: A Self-Referential Agent Framework for Recursive Self-Improvement [112.04307762405669]
  G"odel Agent is a self-evolving framework inspired by the G"odel machine.<n>G"odel Agent can achieve continuous self-improvement, surpassing manually crafted agents in performance, efficiency, and generalizability.
  arXiv  Detail & Related papers  (2024-10-06T10:49:40Z)
• Tradeoffs When Considering Deep Reinforcement Learning for Contingency Management in Advanced Air Mobility [0.0]
  Air transportation is undergoing a rapid evolution globally with the introduction of Advanced Air Mobility (AAM) Increased levels of automation are likely necessary to achieve operational safety and efficiency goals. This paper explores the use of Deep Reinforcement Learning (DRL) which has shown promising performance in complex and high-dimensional environments.
  arXiv  Detail & Related papers  (2024-06-28T19:09:55Z)
• Ego-Foresight: Self-supervised Learning of Agent-Aware Representations for Improved RL [26.169030913260084]
  We present Ego-Foresight, a self-supervised method for disentangling agent and environment based on motion and prediction.<n>Our main finding is self-supervised agent-awareness by visuomotor prediction of the agent improves sample-efficiency and performance of the underlying RL algorithm.
  arXiv  Detail & Related papers  (2024-05-27T13:32:43Z)
• HAZARD Challenge: Embodied Decision Making in Dynamically Changing Environments [93.94020724735199]
  HAZARD consists of three unexpected disaster scenarios, including fire, flood, and wind. This benchmark enables us to evaluate autonomous agents' decision-making capabilities across various pipelines.
  arXiv  Detail & Related papers  (2024-01-23T18:59:43Z)
• Transferable Curricula through Difficulty Conditioned Generators [8.140037969280716]
  Reinforcement learning (RL) has demonstrated superhuman performance in complex tasks such as Starcraft, Go, Chess etc. Recent methods in curricula generation focuses on training RL agents efficiently, yet such methods rely on surrogate measures to track student progress. We introduce a method named. Environment Response Model (PERM) that shows promising results in training RL agents in parameterized environments.
  arXiv  Detail & Related papers  (2023-06-22T16:45:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.