CLEA: Closed-Loop Embodied Agent for Enhancing Task Execution in Dynamic Environments

Large Language Models (LLMs) exhibit remarkable capabilities in the hierarchical decomposition of complex tasks through semantic reasoning. However, their application in embodied systems faces challenges in ensuring reliable execution of subtask sequences and achieving one-shot success in long-term task completion. To address these limitations in dynamic environments, we propose Closed-Loop Embodied Agent (CLEA)—a novel architecture incorporating four specialized open-source LLMs with functional decoupling for closed-loop task management. The framework features two core innovations: (1) Interactive task planner that dynamically generates executable subtasks based on the environmental memory, and (2) Multimodal execution critic employing an evaluation framework to conduct a probabilistic assessment of action feasibility, triggering hierarchical re-planning mechanisms when environmental perturbations exceed preset thresholds. To validate CLEA’s effectiveness, we conduct experiments in a real environment with manipulable objects, using two heterogeneous robots for object search, manipulation, and search-manipulation integration tasks. Across 12 task trials, CLEA outperforms the baseline model, achieving a 67. 3% improvement in success rate and a 52. 8% increase in task completion rate. These results demonstrate that CLEA significantly enhances the robustness of task planning and execution in dynamic environments. Our code is available at https://sp4595.github.io/CLEA/.

Authors

• Mingcong Lei
• Ge Wang
• Yiming Zhao
• Zhixin Mai
• Qing Zhao
• Yao Guo 0002
• Zhen Li 0026
• Shuguang Cui
• Yatong Han
• Jinke Ren

Keywords

• Technological innovation
• Perturbation methods
• Large language models
• Semantics
• Search problems
• Probabilistic logic
• Robustness
• Planning
• Intelligent robots
• Faces
• Dynamic Environment
• Task Execution
• Interactive
• Task Completion
• Language Model
• Manipulation Tasks
• Search Task
• Task Planning
• Improve Success Rates
• Sequence Of Actions
• Simulation Environment
• Visual Observation
• Kinetic Rate
• Robotic System
• Path Planning
• Current Observations
• Multi-agent Systems
• Real-world Environments
• Robotic Platform
• Distinct Objects
• Monte Carlo Tree Search
• Belief State
• Task Failure
• Critical Modulator
• Dynamic Planning
• Environmental Feedback
• Memory Module
• Function Calls
• Recovery Error
• Action Execution