{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,15]],"date-time":"2025-08-15T01:07:41Z","timestamp":1755220061239,"version":"3.43.0"},"reference-count":47,"publisher":"Association for Computing Machinery (ACM)","issue":"1","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["SIGOPS Oper. Syst. Rev."],"published-print":{"date-parts":[[2025,8,4]]},"abstract":"<jats:p>In this paper, we introduce DREAM, Distributed Regional Efficient Agent Management, a novel method using Large Language Models (LLMs) to solve Multi-Agent Pathfinding (MAPF) problems in complicated environments. Our approach splits up the area into various local regions and an LLM agent handles each one of them intelligently in reasoning and decision making. We present some novel designs in our system: 1) Adaptive region management and allocation to regions, supporting the dynamic partitioning of different complexity or density areas. 2) The multi-level LLM-driven agents collaboration framework that enables peer-peer, interLLM coordination and controls for effective monitoring intelligence across a hierarchical path planning organization hierarchy level ensures autonomy whilst improving overall understanding among LLM agents, leading to more accurate planning decisions from real-time analysis. (3) Failurereflection- replanning mechanism integrated within an individual LLM's management scope eventually results continual improvement. (4) LLM agents can do function calling to interact with the typical algorithms also. Our system successfully processes complex and large-scale MAPF scenarios by merging the higher-orderality of reasoning capabilities in LLMs with this novel distributed framework. For instance, the distributed and hierarchical nature of this approach helps to break a high-dimensional MAPF problem into several groups of smaller dimension. As such, this approach also opens up the development of AI language models in more complex robotics and logistics scenarios, potentially changing how multi-agent coordination is done for actual situations.<\/jats:p>","DOI":"10.1145\/3759441.3759446","type":"journal-article","created":{"date-parts":[[2025,8,6]],"date-time":"2025-08-06T14:43:44Z","timestamp":1754491424000},"page":"24-33","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["DREAM: Distributed Regional Efficient Agent Management with LLMs for Online Multi-Agent Pathfinding"],"prefix":"10.1145","volume":"59","author":[{"given":"Rui","family":"Yang","sequence":"first","affiliation":[]},{"given":"Rajiv","family":"Gupta","sequence":"additional","affiliation":[]}],"member":"320","published-online":{"date-parts":[[2025,8,6]]},"reference":[{"key":"e_1_2_1_1_1","first-page":"151","volume-title":"Int. Symp. Combinatorial Search","volume":"10","author":"Stern R.","year":"2019","unstructured":"R. Stern, N. Sturtevant, A. Felner, et al., \"Multi-agent pathfinding: Definitions, variants, and benchmarks,\" in Proc. Int. Symp. Combinatorial Search, vol. 10, 2019, pp. 151-158."},{"key":"e_1_2_1_2_1","first-page":"96","volume-title":"Dolgoprudny, Russia","author":"Stern R.","year":"2019","unstructured":"R. Stern, et al., \"Multi-agent path finding-an overview,\" in Artificial Intelligence: 5th RAAI Summer School, Dolgoprudny, Russia, July 4-7, 2019, Tutorial Lectures, 2019, pp. 96-115."},{"doi-asserted-by":"publisher","key":"e_1_2_1_3_1","DOI":"10.5555\/3398761.3398959"},{"doi-asserted-by":"publisher","key":"e_1_2_1_4_1","DOI":"10.1016\/j.artint.2021.103574"},{"key":"e_1_2_1_5_1","first-page":"12353","volume-title":"AAAI Conf. Artificial Intelligence","volume":"35","author":"Li J.","year":"2021","unstructured":"J. Li, W. Ruml, and S. Koenig, \"EECBS: A boundedsuboptimal search for multi-agent path finding,\" in Proc. AAAI Conf. Artificial Intelligence, vol. 35, 2021, pp. 12353-12362."},{"issue":"6","key":"e_1_2_1_6_1","first-page":"1163","article-title":"Prioritized planning algorithms for trajectory coordination of multiple mobile robots","volume":"27","author":"Phillips M.","year":"2011","unstructured":"M. Phillips, V. Hwang, S. Chitta, and M. Likhachev, \"Prioritized planning algorithms for trajectory coordination of multiple mobile robots,\" IEEE Trans. Robotics, vol. 27, no. 6, pp. 1163-1173, 2011.","journal-title":"IEEE Trans. Robotics"},{"key":"e_1_2_1_7_1","first-page":"7643","volume-title":"AAAI Conf. Artificial Intelligence","volume":"33","author":"Ma H.","year":"2019","unstructured":"H. Ma, D. Harabor, P. J Stuckey, J. Li, and S. Koenig, \"Searching with consistent prioritization for multi-agent path finding,\" in Proc. AAAI Conf. Artificial Intelligence, vol. 33, 2019, pp. 7643-7650."},{"key":"e_1_2_1_8_1","first-page":"11655","volume-title":"AAAI Conf. Artificial Intelligence","volume":"37","author":"Okumura K.","year":"2023","unstructured":"K. Okumura, \"Lacam: Search-based algorithm for quick multi-agent pathfinding,\" in Proc. AAAI Conf. Artificial Intelligence, vol. 37, 2023, pp. 11655-11662."},{"doi-asserted-by":"publisher","key":"e_1_2_1_9_1","DOI":"10.1016\/j.artint.2014.11.006"},{"key":"e_1_2_1_10_1","first-page":"83","volume-title":"Int. Conf. Automated Planning and Scheduling","volume":"28","author":"Felner A.","year":"2018","unstructured":"A. Felner, J. Li, et al., \"Adding heuristics to conflictbased search for multi-agent path finding,\" in Proc. Int. Conf. Automated Planning and Scheduling, vol. 28, 2018, pp. 83-87."},{"key":"e_1_2_1_11_1","first-page":"193","volume-title":"Int. Conf. Automated Planning and Scheduling","volume":"30","author":"Li J.","year":"2020","unstructured":"J. Li, G. Gange, D. Harabor, P. J. Stuckey, H. Ma, and S. Koenig, \"New techniques for pairwise symmetry breaking in multi-agent path finding,\" in Proc. Int. Conf. Automated Planning and Scheduling, vol. 30, 2020, pp. 193-201."},{"key":"e_1_2_1_12_1","first-page":"757","volume-title":"17th Int. Conf. Autonomous Agents and MultiAgent Systems","author":"H\u00f6nig W.","year":"2018","unstructured":"W. H\u00f6nig, S. Kiesel, A. Tinka, J. W. Durham, and N. Ayanian, \"Conflict-based search with optimal task assignment,\" in Proc. 17th Int. Conf. Autonomous Agents and MultiAgent Systems, 2018, pp. 757-765."},{"key":"e_1_2_1_13_1","first-page":"1129","volume-title":"29th Int. Joint Conf. Artificial Intelligence","author":"Li J.","year":"2020","unstructured":"J. Li, D. Harabor, P. J. Stuckey, A. Felner, H. Ma, and S. Koenig, \"Disjoint splitting for multi-agent path finding with conflict-based search,\" in Proc. 29th Int. Joint Conf. Artificial Intelligence, 2020, pp. 1129-1135."},{"key":"e_1_2_1_14_1","first-page":"740","volume-title":"24th Int. Joint Conf. Artificial Intelligence","author":"Boyarski E.","year":"2015","unstructured":"E. Boyarski, A. Felner, R. Stern, G. Sharon, D. Tolpin, O. Betzalel, and S. E. Shimony, \"ICBS: Improved conflictbased search algorithm for multi-agent pathfinding,\" in Proc. 24th Int. Joint Conf. Artificial Intelligence, 2015, pp. 740-746."},{"doi-asserted-by":"publisher","key":"e_1_2_1_15_1","DOI":"10.1016\/j.artint.2014.11.001"},{"key":"e_1_2_1_16_1","first-page":"11272","volume-title":"35th AAAI Conf. Artificial Intelligence","author":"Li J.","year":"2021","unstructured":"J. Li, A. Tinka, S. Kiesel, J. W. Durham, T. K. S. Kumar, and S. Koenig, \"Lifelong multi-agent path finding in large-scale warehouses,\" in Proc. 35th AAAI Conf. Artificial Intelligence, 2021, pp. 11272-11281."},{"key":"e_1_2_1_17_1","first-page":"117","volume-title":"Proc. 1st Artificial Intelligence and Interactive Digital Entertainment Conf.","author":"Silver D.","year":"2005","unstructured":"D. Silver, \"Cooperative pathfinding,\" in Proc. 1st Artificial Intelligence and Interactive Digital Entertainment Conf., 2005, pp. 117-122."},{"doi-asserted-by":"publisher","key":"e_1_2_1_18_1","DOI":"10.1109\/LRA.2019.2903261"},{"key":"e_1_2_1_19_1","first-page":"3605","volume-title":"31st AAAI Conf. Artificial Intelligence","author":"Ma H.","year":"2017","unstructured":"H. Ma, T. K. S. Kumar, and S. Koenig, \"Multi-agent path finding with delay probabilities,\" in Proc. 31st AAAI Conf. Artificial Intelligence, 2017, pp. 3605-3612."},{"key":"e_1_2_1_20_1","first-page":"7627","volume-title":"33rd AAAI Conf. Artificial Intelligence","author":"Li J.","year":"2019","unstructured":"J. Li, P. Surynek, A. Felner, H. Ma, T. K. S. Kumar, and S. Koenig, \"Multi-agent path finding for large agents,\" in Proc. 33rd AAAI Conf. Artificial Intelligence, 2019, pp. 7627-7634."},{"key":"e_1_2_1_21_1","first-page":"477","volume-title":"26th Int. Conf. Automated Planning and Scheduling","author":"H\u00f6nig W.","year":"2016","unstructured":"W. H\u00f6nig, T. K. S. Kumar, L. Cohen, H. Ma, H. Xu, N. Ayanian, and S. Koenig, \"Multi-agent path finding with kinematic constraints,\" in Proc. 26th Int. Conf. Automated Planning and Scheduling, 2016, pp. 477-485."},{"key":"e_1_2_1_22_1","first-page":"1443","volume-title":"27th AAAI Conf. Artificial Intelligence","author":"Yu J.","year":"2013","unstructured":"J. Yu and S. M. LaValle, \"Structure and intractability of optimal multi-robot path planning on graphs,\" in Proc. 27th AAAI Conf. Artificial Intelligence, 2013, pp. 1443- 1449."},{"doi-asserted-by":"publisher","key":"e_1_2_1_23_1","DOI":"10.1613\/jair.1.11734"},{"key":"e_1_2_1_24_1","first-page":"323","volume-title":"30th Int. Conf. Automated Planning and Scheduling","author":"Zhang H.","year":"2020","unstructured":"H. Zhang, J. Li, P. Surynek, S. Koenig, and T. K. S. Kumar, \"Multi-agent path finding with mutex propagation,\" in Proc. 30th Int. Conf. Automated Planning and Scheduling, 2020, pp. 323-332."},{"key":"e_1_2_1_25_1","first-page":"6087","volume-title":"33rd AAAI Conf. Artificial Intelligence","author":"Li J.","year":"2019","unstructured":"J. Li, D. Harabor, P. J. Stuckey, H. Ma, and S. Koenig, \"Symmetry-breaking constraints for grid-based multiagent path finding,\" in Proc. 33rd AAAI Conf. Artificial Intelligence, 2019, pp. 6087-6095."},{"key":"e_1_2_1_26_1","first-page":"175","article-title":"Distributed optimization with pairwise constraints and its application to multi-robot path planning,\" in Robotics","author":"Bhattacharya S.","year":"2010","unstructured":"S. Bhattacharya, V. Kumar, and M. Likhachev, \"Distributed optimization with pairwise constraints and its application to multi-robot path planning,\" in Robotics: Science and Systems, 2010, pp. 175-182.","journal-title":"Science and Systems"},{"doi-asserted-by":"publisher","key":"e_1_2_1_27_1","DOI":"10.1109\/TRO.2018.2853613"},{"doi-asserted-by":"publisher","key":"e_1_2_1_28_1","DOI":"10.1177\/0278364917719333"},{"doi-asserted-by":"publisher","key":"e_1_2_1_29_1","DOI":"10.1016\/j.artint.2012.11.006"},{"key":"e_1_2_1_30_1","first-page":"29","volume-title":"Int. Conf. Automated Planning and Scheduling","author":"Atzmon D.","year":"2020","unstructured":"D. Atzmon, R. Stern, A. Felner, N. R. Sturtevant, and S. Koenig, \"Probabilistic robust multi-agent path finding,\" in Proc. Int. Conf. Automated Planning and Scheduling, 2020, pp. 29-37."},{"key":"e_1_2_1_31_1","first-page":"442","volume-title":"28th Int. Joint Conf. Artificial Intelligence","author":"Li J.","year":"2019","unstructured":"J. Li, A. Felner, E. Boyarski, H. Ma, and S. Koenig, \"Improved heuristics for multi-agent path finding with conflict-based search,\" in Proc. 28th Int. Joint Conf. Artificial Intelligence, 2019, pp. 442-449."},{"key":"e_1_2_1_32_1","first-page":"290","volume-title":"27th AAAI Conf. Artificial Intelligence","author":"Erdem E.","year":"2013","unstructured":"E. Erdem, D. G. Kisa, U. Oztok, and P. Schueller, \"A general formal framework for pathfinding problems with multiple agents,\" in Proc. 27th AAAI Conf. Artificial Intelligence, 2013, pp. 290-296."},{"key":"e_1_2_1_33_1","first-page":"151","volume-title":"12th Int. Symp. Combinatorial Search","author":"Stern R.","year":"2019","unstructured":"R. Stern, N. R. Sturtevant, D. Atzmon, T. Walker, J. Li, L. Cohen, H. Ma, T. K. S. Kumar, A. Felner, and S. Koenig, \"Multi-agent pathfinding: Definitions, variants, and benchmarks,\" in Proc. 12th Int. Symp. Combinatorial Search, 2019, pp. 151-159."},{"key":"e_1_2_1_34_1","first-page":"7732","volume-title":"33rd AAAI Conf. Artificial Intelligence","author":"Svancara J.","year":"2019","unstructured":"J. Svancara, M. Vlk, R. Stern, D. Atzmon, and R. Bart\u00e1k, \"Online multi-agent pathfinding,\" in Proc. 33rd AAAI Conf. Artificial Intelligence, 2019, pp. 7732-7739."},{"key":"e_1_2_1_35_1","first-page":"668","volume-title":"22nd Int. Joint Conf. Artificial Intelligence","author":"Standley T. S.","year":"2011","unstructured":"T. S. Standley and R. Korf, \"Complete algorithms for cooperative pathfinding problems,\" in Proc. 22nd Int. Joint Conf. Artificial Intelligence, 2011, pp. 668-673."},{"key":"e_1_2_1_36_1","volume-title":"Why solving multi-agent path finding with large language models has not succeeded yet,\" arXiv preprint arXiv:2401.03630","author":"Chen W.","year":"2024","unstructured":"W. Chen, S. Koenig, and B. N. Dilkina, \"Why solving multi-agent path finding with large language models has not succeeded yet,\" arXiv preprint arXiv:2401.03630, 2024."},{"key":"e_1_2_1_37_1","volume-title":"LLM+ P: Empowering Large Language Models with Optimal Planning Proficiency,\" arXiv preprint arXiv:2304.11477","author":"Liu B.","year":"2023","unstructured":"B. Liu, Y. Jiang, X. Zhang, Q. Liu, S. Zhang, J. Biswas, and P. Stone, \"LLM+ P: Empowering Large Language Models with Optimal Planning Proficiency,\" arXiv preprint arXiv:2304.11477, 2023."},{"key":"e_1_2_1_38_1","volume-title":"RoCo: Dialectic Multi- Robot Collaboration with Large Language Models,\" arXiv preprint arXiv:2307.04738","author":"Mandi Z.","year":"2023","unstructured":"Z. Mandi, S. Jain, and S. Song, \"RoCo: Dialectic Multi- Robot Collaboration with Large Language Models,\" arXiv preprint arXiv:2307.04738, 2023."},{"key":"e_1_2_1_39_1","volume-title":"A Language Agent for Autonomous Driving,\" arXiv preprint arXiv:2311.10813","author":"Mao J.","year":"2023","unstructured":"J. Mao, J. Ye, Y. Qian, M. Pavone, and Y. Wang, \"A Language Agent for Autonomous Driving,\" arXiv preprint arXiv:2311.10813, 2023."},{"key":"e_1_2_1_40_1","volume-title":"Evaluating multiagent coordination abilities in large language models,\" arXiv preprint arXiv:2310.03903","author":"Agashe S.","year":"2023","unstructured":"S. Agashe, Y. Fan, and X. E. Wang, \"Evaluating multiagent coordination abilities in large language models,\" arXiv preprint arXiv:2310.03903, 2023."},{"key":"e_1_2_1_41_1","volume-title":"Scalable Multi-Robot Collaboration with Large Language Models: Centralized or Decentralized Systems?\" arXiv preprint arXiv:2309.15943","author":"Chen Y.","year":"2023","unstructured":"Y. Chen, J. Arkin, Y. Zhang, N. Roy, and C. Fan, \"Scalable Multi-Robot Collaboration with Large Language Models: Centralized or Decentralized Systems?\" arXiv preprint arXiv:2309.15943, 2023."},{"key":"e_1_2_1_42_1","volume-title":"On the Planning Abilities of Large Language Models-A Critical Investigation,\" arXiv preprint arXiv:2305.15771","author":"Valmeekam K.","year":"2023","unstructured":"K. Valmeekam, M. Marquez, S. Sreedharan, and S. Kambhampati, \"On the Planning Abilities of Large Language Models-A Critical Investigation,\" arXiv preprint arXiv:2305.15771, 2023."},{"doi-asserted-by":"publisher","key":"e_1_2_1_43_1","DOI":"10.18653\/v1\/2023.emnlp-main.13"},{"issue":"2","key":"e_1_2_1_44_1","first-page":"144","article-title":"Benchmarks for Grid-Based Pathfinding","volume":"4","author":"Sturtevant N.","year":"2012","unstructured":"N. Sturtevant, \"Benchmarks for Grid-Based Pathfinding,\" IEEE Trans. Computational Intelligence and AI in Games, vol. 4, no. 2, pp. 144-148, 2012.","journal-title":"IEEE Trans. Computational Intelligence and AI in Games"},{"key":"e_1_2_1_45_1","first-page":"4382","volume-title":"Int. Joint Conf. Artificial Intelligence (IJCAI)","author":"Li J.","year":"2019","unstructured":"J. Li, T. T. T. Le, and H. Ma, \"EECBS: Enhanced Conflict-Based Search for Multi-Agent Path Finding,\" in Proc. Int. Joint Conf. Artificial Intelligence (IJCAI), 2019, pp. 4382-4389."},{"key":"e_1_2_1_46_1","first-page":"6572","article-title":"PIBT: Priority-Based Iterative Bounded Technique for Multi- Agent Path Finding","volume":"33","author":"Okumura K.","year":"2019","unstructured":"K. Okumura, A. Akiyama, and M. Nakashima, \"PIBT: Priority-Based Iterative Bounded Technique for Multi- Agent Path Finding,\" in Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, 2019, pp. 6572- 6579.","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"e_1_2_1_47_1","volume-title":"Abu Dhabi","author":"Yang R.","year":"2024","unstructured":"R. Yang and R. Gupta, \"P4: Pruning and Predictionbased Priority Planning,\" in IEEE\/RSJ International Conference on Intelligent Robots and Systems, Abu Dhabi, 2024, 8 pages."}],"container-title":["ACM SIGOPS Operating Systems Review"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3759441.3759446","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T19:50:24Z","timestamp":1754596224000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3759441.3759446"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,4]]},"references-count":47,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,8,4]]}},"alternative-id":["10.1145\/3759441.3759446"],"URL":"https:\/\/doi.org\/10.1145\/3759441.3759446","relation":{},"ISSN":["0163-5980"],"issn-type":[{"type":"print","value":"0163-5980"}],"subject":[],"published":{"date-parts":[[2025,8,4]]},"assertion":[{"value":"2025-08-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}