{"paper":{"title":"Hybrid LLM-based Intelligent Framework for Robot Task Scheduling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Hybrid LLM framework with generator and supervisor agents creates optimized, adaptive task schedules for construction robots.","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Haonan Duan, Subhabrata Das, Swayamjit Saha, Xiao-Yang Liu","submitted_at":"2026-05-15T00:04:38Z","abstract_excerpt":"This study introduces intelligent frameworks that use Large Language Models (LLMs) to improve task scheduling for construction robots. The LLM is fed with key data about the desired task, such as agent action abilities, and the desired end goal to be achieved. A well-balanced allocation strategy is developed, optimizing both time efficiency and resource utilization. Our system utilizes a Natural Language Processing interface to streamline communication with construction professionals and adapt in real-time to unexpected site conditions. We concurrently use two LLM agents, specifically generato"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Our results highlight that the implementation of LLMs is crucial in construction operational tasks including robots.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That providing agent action abilities and end goals to the generator and supervisor LLMs will produce a well-balanced, real-time adaptive schedule that actually optimizes time and resources under unpredictable site conditions.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Hybrid LLM framework using generator and supervisor agents to optimize task scheduling for construction robots, evaluated on a simple scenario with reported metrics.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Hybrid LLM framework with generator and supervisor agents creates optimized, adaptive task schedules for construction robots.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"82942540e7dcea6e268532be3a1b2abfb46862a8836fc300946ee00c472bac75"},"source":{"id":"2605.15486","kind":"arxiv","version":1},"verdict":{"id":"2f71d57d-f8b0-4d5f-81e9-ea6a22359191","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T16:16:03.375259Z","strongest_claim":"Our results highlight that the implementation of LLMs is crucial in construction operational tasks including robots.","one_line_summary":"Hybrid LLM framework using generator and supervisor agents to optimize task scheduling for construction robots, evaluated on a simple scenario with reported metrics.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That providing agent action abilities and end goals to the generator and supervisor LLMs will produce a well-balanced, real-time adaptive schedule that actually optimizes time and resources under unpredictable site conditions.","pith_extraction_headline":"Hybrid LLM framework with generator and supervisor agents creates optimized, adaptive task schedules for construction robots."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.15486/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T16:31:18.232957Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T16:25:40.361072Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"cited_work_retraction","ran_at":"2026-05-19T14:51:57.423083Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T14:21:54.075118Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"citation_quote_validity","ran_at":"2026-05-19T13:49:41.402389Z","status":"skipped","version":"0.1.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T13:33:22.651428Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"0a1edd4755b9c7c7b845107af89eea4090101214f8b4836d7f154f989a32fb94"},"references":{"count":16,"sample":[{"doi":"","year":2022,"title":"Zhao, S., Wang, Q., Fang, X., Liang, W., Cao, Y ., Zhao, C., ... & Wang, K. (2022). Application and development of autonomous robots in concrete construction: Challenges and opportunities. Drones, 6(1","work_id":"d0f3e9be-a5b3-49ec-b1b2-51d821a0516f","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Gemma 3 Technical Report","work_id":"f93e08bf-9e96-409b-8ac6-b8385fd17fd7","ref_index":2,"cited_arxiv_id":"2503.19786","is_internal_anchor":true},{"doi":"","year":2025,"title":"”The Llama 4 herd: The beginning of a new era of na- tively multimodal AI innovation — Meta.” Accessed Apr. 08, 2025. [Online]. Available: https://ai.meta.com/blog/llama-4- multimodal-intelligence/","work_id":"b40d7d30-e4ac-4ecd-9a81-eedf40aad2f5","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Q., Sablayrolles, A., Mensch, A., Bamford, C., Chap- lot, D","work_id":"eb5e1305-ad11-4875-ad8d-ad8b8f697599","ref_index":4,"cited_arxiv_id":"2310.06825","is_internal_anchor":true},{"doi":"","year":2023,"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","ref_index":5,"cited_arxiv_id":"2303.08774","is_internal_anchor":true}],"resolved_work":16,"snapshot_sha256":"12a9ed22b4f874e6db682f022934e2eb82ff35de636ffc59fcf8487fe42082f2","internal_anchors":3},"formal_canon":{"evidence_count":2,"snapshot_sha256":"1dc6466916720d96dec796698b64abf9d5bc9cc20ed500fd7eaeefc0b26e2072"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}