Download pdf
A Metacognitive Evaluation Framework for Embodied Intelligent Agents
- 1 Tomsk State University, Tomsk, Russia
* Author to whom correspondence should be addressed.
Abstract
The study introduces a novel evaluation system designed to measure the metacognitive abilities of embodied agents. The system incorporates multiple metrics—including task success rate, self-monitoring accuracy (measured by AUC), error detection speed, and confidence calibration error—to provide a comprehensive assessment of an agent’s internal monitoring and self-regulatory processes. Experiments were conducted in simulated environments (using Meta-World, etc.) and on a real robotic platform performing target grasping tasks. Two types of agents were compared: baseline agents relying solely on external feedback and agents enhanced with integrated metacognitive modules. The results demonstrate that agents with metacognitive capabilities consistently achieve higher performance, exhibit more precise self-monitoring, and respond more swiftly to unexpected events. This evaluation system serves as a robust tool for assessing metacognitive functions and offers promising implications for the development of more adaptable and reliable autonomous systems in dynamic environments, thus significantly enhancing overall system performance continuously.
Keywords
Metacognition, Embodied Agents, Self-Monitoring, Error Detection, Autonomous Systems
[1]. Liu, Y., Chen, W., Bai, Y., Liang, X., Li, G., Gao, W. and Lin, L. (2024) Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AI. arXiv preprint. https://arxiv.org/abs/2407.06886
[2]. Valiente, R. and Pilly, P.K. (2024) Metacognition for Unknown Situations and Environments (MUSE). arXiv preprint. https://arxiv.org/abs/2411.13537
[3]. Leidner, D. (2024) Toward Robotic Metacognition: Redefining Self-Awareness in an Era of Vision-Language Models. In ICRA@ 40 40th Anniversary of the IEEE International Conference on Robotics and Automation.
[4]. Cox, M., Alavi, Z., Dannenhauer, D., Eyorokon, V., Munoz-Avila, H. and Perlis, D. (2016) MIDCA: A Metacognitive, Integrated Dual-Cycle Architecture for Self-Regulated Autonomy. In Proceedings of the AAAI Conference on Artificial Intelligence, 30(1).
[5]. Haidarian, H., Dinalankara, W., Fults, S., Wilson, S., Perlis, D. and Anderson, M. (2010) The Metacognitive Loop: An Architecture for Building Robust Intelligent Systems. AAAI Fall Symposium - Technical Report.
[6]. Rabiee, S. and Biswas, J. (2023) Introspective Perception for Mobile Robots. Artificial Intelligence, 324, 103999.
[7]. Loftus, T.J., Tighe, P.J., Filiberto, A.C., Efron, P.A., Brakenridge, S.C., Mohr, A.M., Rashidi, P., Upchurch, G.R. and Bihorac, A. (2020) Artificial Intelligence and Surgical Decision-Making. JAMA Surgery, 155(2), 148–158.
[8]. Bhattacharyya, R., Colombatto, C., Fleming, S., Posner, I. and Hawes, N. (2023) Investigating the Role of Metacognition for Joint Decision-Making in Human-Robot Collaboration.
[9]. Didolkar, A., Goyal, A., Ke, N.R., Guo, S., Valko, M., Lillicrap, T., Jimenez Rezende, D., Bengio, Y., Mozer, M.C. and Arora, S. (2024) Metacognitive Capabilities of LLMs: An Exploration in Mathematical Problem Solving. Advances in Neural Information Processing Systems, 37, 19783–19812.
[10]. Li, M., Zhao, S., Wang, Q., Wang, K., Zhou, Y., Srivastava, S., Gokmen, C., Lee, T., Li, E.L., Zhang, R. et al. (2024) Embodied Agent Interface: Benchmarking LLMs for Embodied Decision Making. Advances in Neural Information Processing Systems, 37, 100428–100534.
[11]. Kronsted, C., Kugele, S., Neemeh, Z.A., Ryan Jr, K.J. and Franklin, S. (2022) Embodied Intelligence: Smooth Coping in the Learning Intelligent Decision Agent Cognitive Architecture. Frontiers in Psychology, 13, 846931.
[12]. Dorsch, J. (2022) Embodied Metacognition: How We Feel Our Hearts to Know Our Minds. The University of Edinburgh.
[13]. Anil Meera, A. and Lanillos, P. (2024) Towards Metacognitive Robot Decision Making for Tool Selection. In Buckley, C.L., Cialfi, D., Lanillos, P., Ramstead, M., Sajid, N., Shimazaki, H., Verbelen, T. and Wisse, M. (Eds.), Active Inference, pp. 31–42. Cham: Springer Nature Switzerland.
[14]. Davis, R.O., Park, T. and Vincent, J. (2022) A Meta-Analytic Review on Embodied Pedagogical Agent Design and Testing Formats. Journal of Educational Computing Research, 61(1), 30–67. https://doi.org/10.1177/07356331221100556
Cite this article
Ling,Y. (2025). A Metacognitive Evaluation Framework for Embodied Intelligent Agents. Applied and Computational Engineering,150,47-52.
Data availability
The datasets used and/or analyzed during the current study will be available from the authors upon reasonable request.
Disclaimer/Publisher's Note
The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of EWA Publishing and/or the editor(s). EWA Publishing and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.
About volume
Volume title: Proceedings of the 3rd International Conference on Software Engineering and Machine Learning
© 2024 by the author(s). Licensee EWA Publishing, Oxford, UK. This article is an open access article distributed under the terms and
conditions of the Creative Commons Attribution (CC BY) license. Authors who
publish this series agree to the following terms:
1. Authors retain copyright and grant the series right of first publication with the work simultaneously licensed under a Creative Commons
Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this
series.
2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the series's published
version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial
publication in this series.
3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and
during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See
Open access policy for details).