Agentic LLM-based robotic systems for real-world applications: a review on their agenticness and ethics
Agentic AI refers to autonomous systems that can perceive their environment, make decisions, and take actions to achieve goals with minimal or no human intervention. Recent advances in Large Language Models (LLMs) have opened new pathways to imbue robots with such “agentic” behaviors by leveraging t...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-08-01
|
| Series: | Frontiers in Robotics and AI |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/frobt.2025.1605405/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849735488920879104 |
|---|---|
| author | Emmanuel K. Raptis Emmanuel K. Raptis Athanasios Ch. Kapoutsis Athanasios Ch. Kapoutsis Elias B. Kosmatopoulos Elias B. Kosmatopoulos |
| author_facet | Emmanuel K. Raptis Emmanuel K. Raptis Athanasios Ch. Kapoutsis Athanasios Ch. Kapoutsis Elias B. Kosmatopoulos Elias B. Kosmatopoulos |
| author_sort | Emmanuel K. Raptis |
| collection | DOAJ |
| description | Agentic AI refers to autonomous systems that can perceive their environment, make decisions, and take actions to achieve goals with minimal or no human intervention. Recent advances in Large Language Models (LLMs) have opened new pathways to imbue robots with such “agentic” behaviors by leveraging the LLMs’ vast knowledge and reasoning capabilities for planning and control. This survey provides the first comprehensive exploration of LLM-based robotic systems integration into agentic behaviors that have been validated in real-world applications. We systematically categorized these systems across navigation, manipulation, multi-agent, and general-purpose multi-task robots, reflecting the range of applications explored. We introduce a novel, first-of-its-kind agenticness classification that evaluates existing LLM-driven robotic works based on their degree of autonomy, goal-directed behavior, adaptability, and decision-making. Additionally, central to our contribution is an evaluation framework explicitly addressing ethical, safety, and transparency principles—including bias mitigation, fairness, robustness, safety guardrails, human oversight, explainability, auditability, and regulatory compliance. By jointly mapping the landscape of agentic capabilities and ethical safeguards, we uncover key gaps, tensions, and design trade-offs in current approaches. We believe that this work serves as both a diagnostic and a call to action: as LLM-empowered robots grow more capable, ensuring they remain comprehensible, controllable, and aligned with societal norms is not optional—it is essential. |
| format | Article |
| id | doaj-art-7d77e33ca3ea4cf5b8f69550d6a48348 |
| institution | DOAJ |
| issn | 2296-9144 |
| language | English |
| publishDate | 2025-08-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Robotics and AI |
| spelling | doaj-art-7d77e33ca3ea4cf5b8f69550d6a483482025-08-20T03:07:33ZengFrontiers Media S.A.Frontiers in Robotics and AI2296-91442025-08-011210.3389/frobt.2025.16054051605405Agentic LLM-based robotic systems for real-world applications: a review on their agenticness and ethicsEmmanuel K. Raptis0Emmanuel K. Raptis1Athanasios Ch. Kapoutsis2Athanasios Ch. Kapoutsis3Elias B. Kosmatopoulos4Elias B. Kosmatopoulos5Information Technologies Institute, The Centre for Research and Technology Hellas, Thessaloniki, GreeceDepartment of Electrical and Computer Engineering, Democritus University of Thrace, Xanthi, GreeceInformation Technologies Institute, The Centre for Research and Technology Hellas, Thessaloniki, GreeceDepartment of Electrical and Computer Engineering, Democritus University of Thrace, Xanthi, GreeceInformation Technologies Institute, The Centre for Research and Technology Hellas, Thessaloniki, GreeceDepartment of Electrical and Computer Engineering, Democritus University of Thrace, Xanthi, GreeceAgentic AI refers to autonomous systems that can perceive their environment, make decisions, and take actions to achieve goals with minimal or no human intervention. Recent advances in Large Language Models (LLMs) have opened new pathways to imbue robots with such “agentic” behaviors by leveraging the LLMs’ vast knowledge and reasoning capabilities for planning and control. This survey provides the first comprehensive exploration of LLM-based robotic systems integration into agentic behaviors that have been validated in real-world applications. We systematically categorized these systems across navigation, manipulation, multi-agent, and general-purpose multi-task robots, reflecting the range of applications explored. We introduce a novel, first-of-its-kind agenticness classification that evaluates existing LLM-driven robotic works based on their degree of autonomy, goal-directed behavior, adaptability, and decision-making. Additionally, central to our contribution is an evaluation framework explicitly addressing ethical, safety, and transparency principles—including bias mitigation, fairness, robustness, safety guardrails, human oversight, explainability, auditability, and regulatory compliance. By jointly mapping the landscape of agentic capabilities and ethical safeguards, we uncover key gaps, tensions, and design trade-offs in current approaches. We believe that this work serves as both a diagnostic and a call to action: as LLM-empowered robots grow more capable, ensuring they remain comprehensible, controllable, and aligned with societal norms is not optional—it is essential.https://www.frontiersin.org/articles/10.3389/frobt.2025.1605405/fullagentic AIlarge language models (LLMs)autonomous robotsintelligent machinesethical AIAI transparency |
| spellingShingle | Emmanuel K. Raptis Emmanuel K. Raptis Athanasios Ch. Kapoutsis Athanasios Ch. Kapoutsis Elias B. Kosmatopoulos Elias B. Kosmatopoulos Agentic LLM-based robotic systems for real-world applications: a review on their agenticness and ethics Frontiers in Robotics and AI agentic AI large language models (LLMs) autonomous robots intelligent machines ethical AI AI transparency |
| title | Agentic LLM-based robotic systems for real-world applications: a review on their agenticness and ethics |
| title_full | Agentic LLM-based robotic systems for real-world applications: a review on their agenticness and ethics |
| title_fullStr | Agentic LLM-based robotic systems for real-world applications: a review on their agenticness and ethics |
| title_full_unstemmed | Agentic LLM-based robotic systems for real-world applications: a review on their agenticness and ethics |
| title_short | Agentic LLM-based robotic systems for real-world applications: a review on their agenticness and ethics |
| title_sort | agentic llm based robotic systems for real world applications a review on their agenticness and ethics |
| topic | agentic AI large language models (LLMs) autonomous robots intelligent machines ethical AI AI transparency |
| url | https://www.frontiersin.org/articles/10.3389/frobt.2025.1605405/full |
| work_keys_str_mv | AT emmanuelkraptis agenticllmbasedroboticsystemsforrealworldapplicationsareviewontheiragenticnessandethics AT emmanuelkraptis agenticllmbasedroboticsystemsforrealworldapplicationsareviewontheiragenticnessandethics AT athanasioschkapoutsis agenticllmbasedroboticsystemsforrealworldapplicationsareviewontheiragenticnessandethics AT athanasioschkapoutsis agenticllmbasedroboticsystemsforrealworldapplicationsareviewontheiragenticnessandethics AT eliasbkosmatopoulos agenticllmbasedroboticsystemsforrealworldapplicationsareviewontheiragenticnessandethics AT eliasbkosmatopoulos agenticllmbasedroboticsystemsforrealworldapplicationsareviewontheiragenticnessandethics |