{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T14:38:35Z","timestamp":1781534315275,"version":"3.54.5"},"reference-count":42,"publisher":"ASME International","issue":"7","license":[{"start":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T00:00:00Z","timestamp":1777420800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.asme.org\/publications-submissions\/publishing-information\/legal-policies"}],"funder":[{"DOI":"10.13039\/501100002855","name":"Ministry of Science and Technology of the People's Republic of China","doi-asserted-by":"publisher","award":["2022YFB4702400"],"award-info":[{"award-number":["2022YFB4702400"]}],"id":[{"id":"10.13039\/501100002855","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["52575300"],"award-info":[{"award-number":["52575300"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["asmedigitalcollection.asme.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>In smart factories, robots play a crucial role in executing critical operations such as material loading and unloading. Task and motion planning (TAMP) approaches enable robots to perform these tasks in an efficient and coordinated manner. Compared with traditional TAMP approaches, large language models (LLMs) demonstrate superior comprehension and reasoning capabilities, making them particularly suitable for solving multitype and interleaved manipulation tasks in smart manufacturing environments. However, the performance of LLMs in TAMP heavily relies on prompt design, for which no unified standard currently exists in the robotics domain. Moreover, LLMs are inherently weak in spatial and temporal reasoning in a manufacturing context, which limits their applicability to practical, domain-specific problem solving. To address these limitations, we propose a tool-augmented LLM approach for TAMP in a smart factory. The core idea is that we first design a unified, domain-specific symbolic prompt engineering scheme tailored for robotic applications. Then, we develop a suite of spatially temporally aware tools to enhance the LLM's reasoning capabilities. Building on these components, the tool-augmented LLM can perform iterative task solving, enabling effective scheduling of machining operations. Both simulation and physical experiments are conducted, and results show that the proposed approach significantly improves the LLM's success rate and generalizability. This work contributes to the development of advanced tool-augmented LLMs for robot task and motion planning in the context of smart manufacturing.<\/jats:p>","DOI":"10.1115\/1.4070577","type":"journal-article","created":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T16:06:55Z","timestamp":1764864415000},"update-policy":"https:\/\/doi.org\/10.1115\/crossmarkpolicy-asme","source":"Crossref","is-referenced-by-count":0,"title":["Task and Motion Planning With Large Language Models Enhanced by Spatially Temporally Aware Tools for Smart Manufacturing"],"prefix":"10.1115","volume":"26","author":[{"given":"Shuo","family":"Liu","sequence":"first","affiliation":[{"id":[{"id":"https:\/\/ror.org\/0220qvk04","id-type":"ROR","asserted-by":"publisher"}],"name":"Shanghai Jiao Tong University Global College, , 800 Dong Chuan Road, , \u00a0 ,","place":["Minhang District, Shanghai, China, 200240"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Youyi","family":"Bi","sequence":"additional","affiliation":[{"id":[{"id":"https:\/\/ror.org\/0220qvk04","id-type":"ROR","asserted-by":"publisher"}],"name":"Shanghai Jiao Tong University Global College, , 800 Dong Chuan Road, , \u00a0 ,","place":["Minhang District, Shanghai, China, 200240"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"33","published-online":{"date-parts":[[2026,4,29]]},"reference":[{"key":"2026042912393095600_CIT0001","doi-asserted-by":"publisher","first-page":"837","DOI":"10.1016\/j.trpro.2021.07.052","article-title":"An Overview of Robot Applications in Automotive Industry","volume":"55","author":"Barto\u0161","year":"2021","journal-title":"Transp. Res. Procedia"},{"issue":"13s","key":"2026042912393095600_CIT0002","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3583136","article-title":"Recent Trends in Task and Motion Planning for Robotics: A Survey","volume":"55","author":"Guo","year":"2023","journal-title":"ACM Comput. Surv."},{"key":"2026042912393095600_CIT0003","first-page":"441","article-title":"Optimal Sequential Task Assignment and Path Finding for Multi-Agent Robotic Assembly Planning","author":"Brown","year":"2020"},{"issue":"7","key":"2026042912393095600_CIT0004","doi-asserted-by":"publisher","first-page":"3094","DOI":"10.3390\/app14073094","article-title":"An Integrated Approach to Precedence-Constrained Multi-Agent Task Assignment and Path Finding for Mobile Robots in Smart Manufacturing","volume":"14","author":"Liu","year":"2024","journal-title":"Appl. Sci."},{"key":"2026042912393095600_CIT0005","first-page":"12086","article-title":"LLM3: Large Language Model-Based Task and Motion Planning With Motion Failure Reasoning","author":"Wang","year":"2024"},{"key":"2026042912393095600_CIT0006","doi-asserted-by":"crossref","first-page":"11316","DOI":"10.18653\/v1\/2024.findings-acl.673","volume-title":"Findings of the Association for Computational Linguistics: ACL 2024","author":"Li","year":"2024"},{"key":"2026042912393095600_CIT0007","article-title":"Evaluating Spatial Understanding of Large Language Models","author":"Yamada","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"issue":"8","key":"2026042912393095600_CIT0008","doi-asserted-by":"publisher","first-page":"198343","DOI":"10.1007\/s11704-024-40678-2","article-title":"Tool Learning With Large Language Models: A Survey","volume":"19","author":"Qu","year":"2025","journal-title":"Front. Comput. Sci."},{"issue":"1","key":"2026042912393095600_CIT0009","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1016\/j.cirp.2024.04.002","article-title":"An LLM-Based Approach for Enabling Seamless Human-Robot Collaboration in Assembly","volume":"73","author":"Gkournelos","year":"2024","journal-title":"CIRP Ann."},{"key":"2026042912393095600_CIT0010","first-page":"371","article-title":"Understanding Large-Language Model (LLM)-Powered Human-Robot Interaction","author":"Kim","year":"2024"},{"issue":"5","key":"2026042912393095600_CIT0011","doi-asserted-by":"publisher","first-page":"050801","DOI":"10.1115\/1.4068235","article-title":"Toward Embodied Intelligence-Enabled Human\u2013Robot Symbiotic Manufacturing: A Large Language Model-Based Perspective","volume":"25","author":"Dong","year":"2025","journal-title":"ASME J. Comput. Inf. Sci. Eng."},{"issue":"2","key":"2026042912393095600_CIT0012","doi-asserted-by":"publisher","first-page":"021009","DOI":"10.1115\/1.4067333","article-title":"DesignQA: A Multimodal Benchmark for Evaluating Large Language Models' Understanding of Engineering Documentation","volume":"25","author":"Doris","year":"2024","journal-title":"ASME J. Comput. Inf. Sci. Eng."},{"key":"2026042912393095600_CIT0013","article-title":"Incorporating Large Language Models Into Production Systems for Enhanced Task Automation and Flexibility","author":"Xia","year":"2024"},{"key":"2026042912393095600_CIT0014","article-title":"Llumnix: Dynamic Scheduling for Large Language Model Serving","author":"Sun","year":"2024"},{"key":"2026042912393095600_CIT0015","first-page":"369","article-title":"ExeGPT: Constraint-Aware Resource Scheduling for LLM Inference","author":"Oh","year":"2024"},{"issue":"2","key":"2026042912393095600_CIT0016","doi-asserted-by":"publisher","DOI":"10.1115\/1.4067085","article-title":"LLM4CAD: Multimodal Large Language Models for Three-Dimensional Computer-Aided Design Generation","volume":"25","author":"Li","year":"2024","journal-title":"ASME J. Comput. Inf. Sci. Eng."},{"issue":"3","key":"2026042912393095600_CIT0017","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1016\/0004-3702(71)90010-5","article-title":"Strips: A New Approach to the Application of Theorem Proving to Problem Solving","volume":"2","author":"Fikes","year":"1971","journal-title":"Artif. Intell."},{"key":"2026042912393095600_CIT0018","doi-asserted-by":"publisher","first-page":"103221","DOI":"10.1016\/j.artint.2019.103221","article-title":"An Introduction to the Planning Domain Definition Language (PDDL): Book Review","volume":"280","author":"Gerevini","year":"2020","journal-title":"Artif. Intell."},{"issue":"1","key":"2026042912393095600_CIT0019","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1146\/annurev-control-091420-084139","article-title":"Integrated Task and Motion Planning","volume":"4","author":"Garrett","year":"2021","journal-title":"Annu. Rev. Control Rob. Auton. Syst."},{"issue":"4","key":"2026042912393095600_CIT0020","doi-asserted-by":"publisher","first-page":"2799","DOI":"10.1109\/TMECH.2024.3452509","article-title":"A Survey of Optimization-Based Task and Motion Planning: From Classical to Learning Approaches","volume":"30","author":"Zhao","year":"2024","journal-title":"IEEE\/ASME Trans. Mechatron."},{"issue":"3","key":"2026042912393095600_CIT0021","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1609\/aimag.v22i3.1572","article-title":"FF: The Fast-Forward Planning System","volume":"22","author":"Hoffmann","year":"2001","journal-title":"AI Magazine"},{"key":"2026042912393095600_CIT0022","first-page":"1235","article-title":"Simultaneous Heuristic Search for Conjunctive Subgoals","author":"Zhu","year":"2005"},{"issue":"5\u20136","key":"2026042912393095600_CIT0023","doi-asserted-by":"publisher","first-page":"593","DOI":"10.1016\/j.artint.2008.11.011","article-title":"A Heuristic Search Approach to Planning With Temporally Extended Preferences","volume":"173","author":"Baier","year":"2009","journal-title":"Artif. Intell."},{"key":"2026042912393095600_CIT0024","first-page":"408","article-title":"Learning Generalized Reactive Policies Using Deep Neural Networks","author":"Groshev","year":"2018"},{"key":"2026042912393095600_CIT0025","first-page":"574","article-title":"Learning Domain-Independent Planning Heuristics With Hypergraph Networks","author":"Shen","year":"2020"},{"key":"2026042912393095600_CIT0026","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1002\/9780470050118.ecse244","volume-title":"Wiley Encyclopedia of Computer Science and Engineering","author":"Wolsey","year":"2008"},{"issue":"3","key":"2026042912393095600_CIT0027","doi-asserted-by":"publisher","first-page":"334","DOI":"10.1057\/palgrave.jors.2600425","article-title":"Nonlinear Programming","volume":"48","author":"Bertsekas","year":"1997","journal-title":"J. Oper. Res. Soc."},{"key":"2026042912393095600_CIT0028","first-page":"10215","article-title":"Graph-Based Reinforcement Learning Meets Mixed Integer Programs: An Application to 3D Robot Assembly Discovery","author":"Funk","year":"2022"},{"key":"2026042912393095600_CIT0029","first-page":"1020","article-title":"Fast MILP-Based Task and Motion Planning for Pick-and-Place With Hard\/Soft Constraints of Collision-Free Route","author":"Kogo","year":"2021"},{"issue":"1","key":"2026042912393095600_CIT0030","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1109\/LCSYS.2020.3001875","article-title":"A Smooth Robustness Measure of Signal Temporal Logic for Symbolic Control","volume":"5","author":"Gilpin","year":"2020","journal-title":"IEEE Control Syst. Lett."},{"key":"2026042912393095600_CIT0031","first-page":"6695","article-title":"AutoTAMP: Autoregressive Task and Motion Planning With LLMs as Translators and Checkers","author":"Chen","year":"2024"},{"issue":"12","key":"2026042912393095600_CIT0032","doi-asserted-by":"publisher","first-page":"120802","DOI":"10.1115\/1.4070095","article-title":"Expanding the Generative Power of Large Language Models for Design Through Formal Design Grammars and Languages","volume":"25","author":"Shea","year":"2025","journal-title":"ASME J. Comput. Inf. Sci. Eng."},{"issue":"11","key":"2026042912393095600_CIT0033","doi-asserted-by":"publisher","first-page":"9407","DOI":"10.1109\/LRA.2024.3460408","article-title":"Action Contextualization: Adaptive Task Planning and Action Tuning Using Large Language Models","volume":"9","author":"Gupta","year":"2024","journal-title":"IEEE Robot. Autom. Lett."},{"key":"2026042912393095600_CIT0034","first-page":"50117","article-title":"ToolQA: A Dataset for LLM Question Answering with External Tools","author":"Zhuang","year":"2023"},{"issue":"4","key":"2026042912393095600_CIT0035","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3704435","article-title":"Tool Learning With Foundation Models","volume":"57","author":"Qin","year":"2024","journal-title":"ACM Comput. Surv."},{"issue":"2","key":"2026042912393095600_CIT0036","doi-asserted-by":"publisher","first-page":"021010","DOI":"10.1115\/1.4067389","article-title":"Integrating Graph Retrieval-Augmented Generation With Large Language Models for Supplier Discovery","volume":"25","author":"Li","year":"2025","journal-title":"ASME J. Comput. Inf. Sci. Eng."},{"key":"2026042912393095600_CIT0037","article-title":"CRITIC: Large Language Models Can Self-Correct With Tool-Interactive Critiquing","author":"Gou","year":"2023"},{"key":"2026042912393095600_CIT0038","doi-asserted-by":"crossref","first-page":"13643","DOI":"10.18653\/v1\/2024.acl-long.737","volume-title":"Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Zhang","year":"2024"},{"key":"2026042912393095600_CIT0039","doi-asserted-by":"crossref","first-page":"19","DOI":"10.63317\/34bfet94yaor","volume-title":"Proceedings of the 2nd Workshop on Mathematical Natural Language Processing @ LREC-COLING 2024","author":"Narin","year":"2024"},{"issue":"6","key":"2026042912393095600_CIT0040","doi-asserted-by":"publisher","first-page":"2514","DOI":"10.1039\/D4SC03921A","article-title":"A Review of Large Language Models and Autonomous Agents in Chemistry","volume":"16","author":"Ramos","year":"2025","journal-title":"Chem. Sci."},{"key":"2026042912393095600_CIT0041","first-page":"90","volume-title":"Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 2: Short Papers)","author":"Theuma","year":"2024"},{"issue":"2","key":"2026042912393095600_CIT0042","doi-asserted-by":"publisher","first-page":"btae075","DOI":"10.1093\/bioinformatics\/btae075","article-title":"GeneGPT: Augmenting Large Language Models With Domain Tools for Improved Access to Biomedical Information","volume":"40","author":"Jin","year":"2024","journal-title":"Bioinformatics"}],"container-title":["Journal of Computing and Information Science in Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/asmedigitalcollection.asme.org\/computingengineering\/article-pdf\/26\/7\/074501\/7574168\/jcise-25-1412.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/asmedigitalcollection.asme.org\/computingengineering\/article-pdf\/26\/7\/074501\/7574168\/jcise-25-1412.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T16:39:38Z","timestamp":1777480778000},"score":1,"resource":{"primary":{"URL":"https:\/\/asmedigitalcollection.asme.org\/computingengineering\/article\/26\/7\/074501\/1229076\/Task-and-Motion-Planning-With-Large-Language"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,29]]},"references-count":42,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2026,7,1]]}},"URL":"https:\/\/doi.org\/10.1115\/1.4070577","relation":{},"ISSN":["1530-9827","1944-7078"],"issn-type":[{"value":"1530-9827","type":"print"},{"value":"1944-7078","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,29]]},"article-number":"074501"}}