[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-82313-en":3,"doc-seo-82313-105":29,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},82313,1374391974564,"Clementine","https://ap-avatar.wpscdn.com/avatar/14000253aa45c000a9e?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779874745381141002",8,"Research & Report","Communication Efficient Digital Twin Coordination for Heterogeneous LLM Embodied Agents over Computing Power Networks","Embodied agent teams powered by heterogeneous large language models (LLMs) require reliable coordination under limited network resources. Existing heterogeneous LLM-agent coordination based on multi-round natural-language dialogue faces escalating communication overhead with team size, quality limits from weak-model short-board effects, and action delays from iterative negotiation. LDT-Coord introduces a lightweight digital twin (DT) that decouples coordination from natural-language reasoning by collecting per-agent action decisions plus structured temporal constraints, then using a training-free rule-based orchestrator to resolve conflicts. Communication reporting is optimized via a constrained POMDP solved with PPO-Lagrangian, achieving comparable task success while cutting overhead by over 70× and retaining robustness under LLM heterogeneity.","Communication-Efficient Digital-Twin Coordination for Heterogeneous LLM Embodied Agents over Computing Power Networks  \nNuocheng Yang, Student Member, IEEE, Sihua Wang, Zihan Chen, Member, IEEE, Tony Q. S. Quek, Fellow, IEEE, and Changchuan Yin, Senior Member, IEEE  \narXiv :2607 .09330v 1 [ cs .AI] 10 Jul 2026  \nAbstract—Embodied agent teams powered by heterogeneous large language models (LLMs) are being widely deployed in physical artificial intelligence such as smart factories, warehouses, and service robotics. To enable collaboration among such an agent team, efficient coordination mechanisms that operate reliably under limited network resources are required. However, existing heterogeneous LLM-agent coordination frameworks that rely on multi-round natural-language-based conversations introduce three coupled challenges. First, inter-agent dialogue incurs communication overhead that grows rapidly with team size. Second, the quality of coordination is constrained by the heterogeneous capabilities of the agent team’s LLMs. Third, agents may suffer from action delays due to iterative negotiation. To address these challenges, we propose LDT-Coord, a networked coordination framework built upon a lightweight digital twin (DT). Specifically, each agent independently selectsits intended action and reports both the action decision anda structured temporal constraint over shared resources to the DT server, thereby decoupling coordination performance from natural-language reasoning ability. Then, DT executes a trainingfree, rule-based orchestrator algorithm to resolve cross-agent conflicts and returns coordination instructions to prevent such conflicts. To further reduce communication overhead, we formulate agent reporting control as a constrained partially observable Markov decision process (C-POMDP) and solve it with the PPO-Lagrangian algorithm. Simulation results show that LDTCoord achieves a task success rate comparable to conventional coordination methods while reducing communication overhead by more than 70 × and maintaining robustness under LLM heterogeneity.  \nIndex Terms—Digital twin, multi-agent coordination, large language models, communication-efficient coordination.  \nI. INTRODUCTION  \nLarge language models (LLMs) have shown strong capability in understanding, reasoning, and generation [1]–[3], which drives an embodied agents framework that can perceive, reflect, and act in a physical artificial intelligence world [4]–[6] . Compared with the conventional centralized framework, where a single server controls each agent, the embodied agents framework can enable distributed intelligence, thereby improving responsiveness, scalability, and robustness in dynamic  \nN. Yang, S. Wang, and C. Yin are with the Beijing Laboratory of Advanced Information Network, and the Beijing Key Laboratory of Network System Architecture and Convergence, Beijing University of Posts and Telecommunications, Beijing 100876, China (emails: {yangnuocheng, sihuawang, [ccyin}@bupt.edu.cn](ccyin}@bupt.edu.cn)).  \nZ. Chen and T. Q. S. Quek are with the Information Systems Technology and Design Pillar, Singapore University of Technology and Design, 487372, Singapore (emails: [zihan_chen@mymail.sutd.edu.sg](zihan_chen@mymail.sutd.edu.sg), [tonyquek@sutd.edu.sg](tonyquek@sutd.edu.sg)).  \nenvironments. As these agents scale from single models to teams, members may run LLMs with heterogeneous capabilities to fit each agent’s task and resource budget [7]–[10] . To enable efficient coordination of such a heterogeneous agent team, several works focus on facilitating information exchange through multiple rounds of natural language (NL) dialogue [11]–[13] . However, building coordination on top of mutual understanding of each other’s NL output exposes three issues. First, at the communication level, the payload of multi-round NL negotiation grows rapidly with team size and number of rounds, which introduces an expensive communication cost. Second, at the heterogeneit","cbCaihu1oJCQEVAI","https://ap.wps.com/l/cbCaihu1oJCQEVAI","pdf",1482048,1,14,"English","en",105,"# Introduction\n## Motivation and challenges\n## Related work and technical routes\n## Digital twin in multi-agent systems","[{\"question\":\"What problem does LDT-Coord target in heterogeneous LLM embodied agent teams?\",\"answer\":\"It targets coordination that remains reliable with limited network resources, avoiding high communication costs, coordination-quality degradation from LLM heterogeneity, and cooperation latency from iterative natural-language negotiation.\"},{\"question\":\"How does LDT-Coord use a digital twin to decouple coordination from natural-language dialogue?\",\"answer\":\"Each agent independently selects its action and reports the action decision along with structured temporal constraints to a DT server; the DT then applies a training-free rule-based orchestrator to resolve cross-agent conflicts and returns coordination instructions.\"},{\"question\":\"How does LDT-Coord reduce communication overhead while maintaining robustness?\",\"answer\":\"It formulates agent reporting control as a constrained partially observable Markov decision process (C-POMDP) and solves it with the PPO-Lagrangian algorithm, yielding more than 70× communication overhead reduction while keeping task success comparable and robust under heterogeneous LLM capabilities.\"}]",1784179542,35,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":27},"communication-efficient-digital-twin-coordination-for-heterogeneous-llm-embodied-agents-over-computing-power-networks","",{"@graph":35,"@context":85},[36,53,68],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/communication-efficient-digital-twin-coordination-for-heterogeneous-llm-embodied-agents-over-computing-power-networks/82313/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-17","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does LDT-Coord target in heterogeneous LLM embodied agent teams?","Question",{"text":75,"@type":76},"It targets coordination that remains reliable with limited network resources, avoiding high communication costs, coordination-quality degradation from LLM heterogeneity, and cooperation latency from iterative natural-language negotiation.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does LDT-Coord use a digital twin to decouple coordination from natural-language dialogue?",{"text":80,"@type":76},"Each agent independently selects its action and reports the action decision along with structured temporal constraints to a DT server; the DT then applies a training-free rule-based orchestrator to resolve cross-agent conflicts and returns coordination instructions.",{"name":82,"@type":73,"acceptedAnswer":83},"How does LDT-Coord reduce communication overhead while maintaining robustness?",{"text":84,"@type":76},"It formulates agent reporting control as a constrained partially observable Markov decision process (C-POMDP) and solves it with the PPO-Lagrangian algorithm, yielding more than 70× communication overhead reduction while keeping task success comparable and robust under heterogeneous LLM capabilities.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":45,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":45,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":45,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":45,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":45,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":45,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":45,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]