An LLM-Driven Closed-Loop Autonomous Learning Framework for Robots Facing Uncovered Tasks in Open Environments

2026-04-24

AI Summary

This work addresses the challenge of enabling robots in open-world environments to autonomously convert executed or observed behaviors into reusable local knowledge without over-relying on repeated interactions with large language models (LLMs). The paper introduces the first LLM-driven closed-loop autonomous learning framework, which first consults a local skill library to determine task feasibility. If no applicable skill exists, the system leverages the LLM for high-level reasoning to guide task decomposition, model selection, data collection, and execution. New strategies are learned from both self-execution and active observation, and upon validation, effective ones are permanently integrated into the local library. This approach enables continuous conversion of experience into reusable local capabilities, substantially reducing LLM invocation frequency. Experiments show that for repeated tasks, average execution time decreases from 7.78 to 6.78 seconds, and LLM calls drop from 1.0 to 0.2 per task.

Technology Category

• Intelligent Robots: Behavior Learning & Control
• Machine Learning: Large Multimodal Models (LMMs)
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

Autonomous robots operating in open environments need the ability to continuously handle tasks that are not covered by predefined local methods. However, existing approaches often rely on repeated large-language-model (LLM) interaction for uncovered tasks, and even successful executions or observed successful external behaviors are not always autonomously transformed into reusable local knowledge. In this paper, we propose an LLM-driven closed-loop autonomous learning framework for robots facing uncovered tasks in open environments. The proposed framework first retrieves the local method library to determine whether a reusable solution already exists for the current task or observed event. If no suitable method is found, it triggers an autonomous learning process in which the LLM serves as a high-level reasoning component for task analysis, candidate model selection, data collection planning, and execution or observation strategy organization. The robot then learns from both self-execution and active observation, performs quasi-real-time training and adjustment, and consolidates the validated result into the local method library for future reuse. Through this recurring closed-loop process, the robot gradually converts both execution-derived and observation-derived experience into reusable local capability while reducing future dependence on repeated external LLM interaction. Results show that the proposed framework reduces execution time and LLM dependence in both repeated-task self-execution and observation-driven settings, for example reducing the average total execution time from 7.7772s to 6.7779s and the average number of LLM calls per task from 1.0 to 0.2 in the repeated-task self-execution experiments.

Problem

• uncovered tasks
• open environments
• autonomous robots
• local knowledge
• LLM dependence

Innovation

• LLM-driven
• closed-loop learning
• autonomous robot
• local knowledge consolidation
• open environments