{"paper":{"title":"An Agentic AI Framework with Large Language Models and Chain-of-Thought for UAV-Assisted Logistics Scheduling with Mobile Edge Computing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"An agentic AI framework with large language models and chain-of-thought reasoning produces consistent mathematical formulations for hybrid UAV logistics and mobile edge computing scheduling, solved via hierarchical proximal policy优化.","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Dusit Niyato, Hanwen Zhang, Malcolm Yoke Hean Low, Wei Zhang, Xin Lou","submitted_at":"2026-05-13T09:13:19Z","abstract_excerpt":"In cloud manufacturing, unmanned aerial vehicles (UAVs) can support both product collection and mobile edge computing (MEC). This joint operation forms a hybrid scheduling problem, where physical logistics decisions are coupled with computational task scheduling. In this paper, UAVs collect finished products from manufacturing stations and transport them back to a central depot. Meanwhile, computational tasks generated by industrial sensor devices at these stations are processed locally, at UAVs, or offloaded via UAVs to the cloud. This coupling makes the problem challenging. A UAV can provide"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"The proposed framework yields more consistent formulations, while the hierarchical PPO achieves full product collection in 99.6% of the last 500 episodes and maintains a 100% deadline satisfaction rate, with more stable performance than the advantage actor-critic approach.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The agentic AI component reliably produces correct and complete mathematical formulations from user input without introducing errors or omissions that would invalidate the subsequent optimization.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"An agentic AI framework with LLMs generates formulations for coupled UAV product collection and MEC task scheduling, solved by hierarchical PPO that reaches 99.6% collection success and 100% deadline compliance in simulations.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"An agentic AI framework with large language models and chain-of-thought reasoning produces consistent mathematical formulations for hybrid UAV logistics and mobile edge computing scheduling, solved via hierarchical proximal policy优化.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"0c7eafb73c375d30fb16b917709aadf8539ceb792a41f3fa6e88cacfb035d327"},"source":{"id":"2605.13221","kind":"arxiv","version":1},"verdict":{"id":"308c9444-dc86-4d53-94fd-d5b764398b26","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T20:06:37.725968Z","strongest_claim":"The proposed framework yields more consistent formulations, while the hierarchical PPO achieves full product collection in 99.6% of the last 500 episodes and maintains a 100% deadline satisfaction rate, with more stable performance than the advantage actor-critic approach.","one_line_summary":"An agentic AI framework with LLMs generates formulations for coupled UAV product collection and MEC task scheduling, solved by hierarchical PPO that reaches 99.6% collection success and 100% deadline compliance in simulations.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The agentic AI component reliably produces correct and complete mathematical formulations from user input without introducing errors or omissions that would invalidate the subsequent optimization.","pith_extraction_headline":"An agentic AI framework with large language models and chain-of-thought reasoning produces consistent mathematical formulations for hybrid UAV logistics and mobile edge computing scheduling, solved via hierarchical proximal policy优化."},"references":{"count":57,"sample":[{"doi":"","year":2025,"title":"Masc: Large language model-based multi-agent scheduling chain for flexible job shop scheduling problem,","work_id":"a8c9dce0-ec55-4256-87f0-8c16f488178e","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2026,"title":"Large language model-empowered dynamic scheduling for intelligent hybrid flow shop using multi-agent deep reinforcement learning,","work_id":"b9d5fb9f-1faa-4adf-81e0-9ea22b681357","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"InFindings of the Association for Compu- tational Linguistics: ACL 2025, pages 17398–17429","work_id":"77436b37-b6a1-4b20-9ca6-a3f7f8d6d3fa","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"H. Abgaryan, A. Harutyunyan, and T. Cazenave, “Llms can schedule,” arXiv:2408.06993, 2024","work_id":"244edbc5-745e-45e4-94f0-59a15b736466","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Preprint (2024)","work_id":"90613e79-870f-4de6-aa30-190882818622","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":57,"snapshot_sha256":"7c37142ec03d65d2150bdc469352b8afb02691f8f5b753834ea133953a44caf7","internal_anchors":1},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}