elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Accessibility | Contact | Deutsch
Fontsize: [-] Text [+]

AgenticNav: A Hierarchical Multi-Agentic System for LLM-Driven Autonomous Problem-Solving in Robotics

Samarathunga, Kaveesha and Gurusinghe, Ranuri and Sivasothynathan, Kugesan and Mars, Jason and LOGEESHAN, V. and Rajakaruna Wanigasekara, Chathura (2026) AgenticNav: A Hierarchical Multi-Agentic System for LLM-Driven Autonomous Problem-Solving in Robotics. IEEE Access. IEEE - Institute of Electrical and Electronics Engineers. doi: 10.1109/ACCESS.2026.3703330. ISSN 2169-3536.

[img] PDF - Only accessible within DLR - Published version
6MB

Official URL: https://ieeexplore.ieee.org/document/11559625

Abstract

A primary challenge in autonomous robotics is bridging the semantic-execution gap in environments where pre-defined plans fail. This paper presents AgenticNav, a cognitive architecture that achieves autonomous problem-solving through a hierarchical Multi-Agentic System (MAS) orchestrated by a Large Language Model (LLM). Within this framework, specialized agents handle environmental perception and task execution, while a stateful agentic hierarchy facilitates failure detection and strategic recovery. When an environmental impasse is encountered, it escalates the execution failure to a strategic level where the LLM re-evaluates the environment’s topological structure to autonomously generate a viable alternative route. Validated in both a high-fidelity simulation and on a physical robot, the system demonstrates the ability to move beyond rigid instruction-following toward true, goal-oriented autonomy. Our results prove that the MAS framework effectively facilitates real-time, reason-based replanning, allowing robots to autonomously resolve complex execution failures in unpredictable real-world settings.

Item URL in elib:https://elib.dlr.de/225067/
Document Type:Article
Title:AgenticNav: A Hierarchical Multi-Agentic System for LLM-Driven Autonomous Problem-Solving in Robotics
Authors:
AuthorsInstitution or Email of AuthorsAuthor's ORCID iDORCID Put Code
Samarathunga, KaveeshaUniversity of MoratuwaUNSPECIFIEDUNSPECIFIED
Gurusinghe, RanuriUniversity of MoratuwaUNSPECIFIEDUNSPECIFIED
Sivasothynathan, KugesanUniversity of MoratuwaUNSPECIFIEDUNSPECIFIED
Mars, JasonUniversity of MichiganUNSPECIFIEDUNSPECIFIED
LOGEESHAN, V.University of MoratuwaUNSPECIFIEDUNSPECIFIED
Rajakaruna Wanigasekara, ChathuraChathura.Wanigasekara (at) dlr.dehttps://orcid.org/0000-0003-4371-6108217680284
Date:June 2026
Journal or Publication Title:IEEE Access
Refereed publication:Yes
Open Access:Yes
Gold Open Access:Yes
In SCOPUS:Yes
In ISI Web of Science:Yes
DOI:10.1109/ACCESS.2026.3703330
Publisher:IEEE - Institute of Electrical and Electronics Engineers
ISSN:2169-3536
Status:Published
Keywords:Multi-Agentic System (MAS), Large Language Models (LLM), Autonomous Problem-Solving, Reason-based Re-planning, Semantic Navigation, Hierarchical Agentic Architecture, Strategic Recovery, Failure Detection
HGF - Research field:other
HGF - Program:other
HGF - Program Themes:other
DLR - Research area:no assignment
DLR - Program:no assignment
DLR - Research theme (Project):no assignment
Location: Geesthacht
Institutes and Institutions:Institute of Maritime Technologies and Propulsion Systems > Energy Converters and Systems
Deposited By: Rajakaruna Wanigasekara, Chathura
Deposited On:15 Jun 2026 08:28
Last Modified:15 Jun 2026 08:29

Repository Staff Only: item control page

Browse
Search
Help & Contact
Information
OpenAIRE Validator logo electronic library is running on EPrints
Website and database design: Copyright © German Aerospace Center (DLR). All rights reserved.