LAPF: LLM-Agent-Based Path Finder Using the UAVScenes Dataset

[2608.15175] LAPF: LLM-Agent-Based Path Finder Using the UAVScenes Dataset Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Robotics arXiv:2608.15175 (cs) [Submitted on 15 Aug 2026] Title: LAPF: LLM-Agent-Based Path Finder Using the UAVScenes Dataset Authors: Yousef Emami , Mohammadhossein Homaei , Hao Zhou , Miguel Gutiérrez Gaitán , Atefeh Hajijamali Arani , Rui Zhang View a PDF of the paper titled LAPF: LLM-Agent-Based Path Finder Using the UAVScenes Dataset, by Yousef Emami and 5 other authors View PDF HTML (experimental) Abstract: Uncrewed aerial vehicles (UAVs) are increasingly deployed for autonomous navigation in complex outdoor environments, where dynamic conditions and mission requirements require intelligent adaptive decision-making. Existing optimization-based, Machine Learning (ML), and Reinforcement Learning (RL) approaches often rely on predefined models or task-specific training, limiting their generalization and adaptability in uncertain scenarios. Recent Large Language Model (LLM)-assisted approaches offer promising reasoning capabilities but remain constrained by limited agentic functionality, including insufficient memory, planning, and tool interaction this http URL paper proposes an LLM-Agent-Based Path Finder (LAPF) framework for autonomous UAV navigation in town-scale outdoor environments. LAPF extends LLM-assisted navigation by integrating perception, memory, planning, and action modules into a closed-loop cognitive architecture. The proposed agent leverages prior navigation experiences, performs Chain-of-Thought (CoT) reasoning, couples each detected hazard to a bounded corrective action, and dynamically refines waypoint decisions based on environmental this http URL three independent trials per method demonstrate that LAPF achieves mean path lengths of 512.83 m and 506.37 m, compared to the straight-line optimum of 497.33 m, corresponding to path length reductions of 17.2% and 15.6% relative to CoT prompting and absolute path efficiencies of 97.1% and 98.1% in open-field and obstacle-injected scenarios, respectively. Furthermore, LAPF is the only evaluated approach that couples every detected hazard to a bounded, metric-neutral corrective action while maintaining near-goal stability, with zero clamp events in both scenarios, whereas CoT prompting increases from 9.7 to 14.0 events. Comments: 15 pages Subjects: Robotics (cs.RO) ; Artificial Intelligence (cs.AI) MSC classes: 53-01 ACM classes: C.2 Cite as: arXiv:2608.15175 [cs.RO] (or arXiv:2608.15175v1 [cs.RO] for this version) https://doi.org/10.48550/arXiv.2608.15175 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Yousef Emami [ view email ] [v1] Sat, 15 Aug 2026 11:28:21 UTC (813 KB) Full-text links: Access Paper: View a PDF of the paper titled LAPF: LLM-Agent-Based Path Finder Using the UAVScenes Dataset, by Yousef Emami and 5 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.RO < prev | next > new | recent | 2026-08 Change to browse by: cs cs.AI References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• LAPF: LLM-Agent-Based Path Finder Using the UAVScenes Dataset#611121
• PDDLCoder: Agentic PDDL Generation for LLM-Assisted Symbolic Planning#622935
• PDDLCoder: Agentic PDDL Generation for LLM-Assisted Symbolic Planning#459714
• LOCAL: Enabling Learning On-device Contiguously for Agent LLMs#615220
• LOCAL: Enabling Learning On-device Contiguously for Agent LLMs#614253