[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-83435-en":3,"doc-seo-83435-105":30,"detail-sidebar-cat-0-en-105":83},{"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":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},83435,1099513958607,"Jiven","https://ap-avatar.wpscdn.com/avatar/100002390cf8733938c?x-image-process=image/resize,m_fixed,w_180,h_180&k=1778829742770036399",8,"Research & Report","Achieving Unanimous Consensus Through Multi Agent Deliberation","Blockchain consensus mechanisms such as Proof-of-Work (PoW) and Proof-of-Stake (PoS) ensure integrity, yet they struggle when decisions require agreement grounded in each participant’s opinions rather than honest-majority or weighted consensus. This paper proposes a deliberation-based mechanism where Large Language Models serve as rational agents that perform structured, multi-round discussions. The method provides unanimous consensus for definitive questions and graded consensus for prioritized policy decisions. A formalization and analysis cover blockchain property preservation, adversarial behavior, stalled deliberations, and consensus confidence. Experiments demonstrate convergence, block properties, and accuracy for deliberative decision-making.","Achieving Unanimous Consensus Through Multi-Agent Deliberation  \nApurba Pokharel University of North Texas [apurba.pokharel@unt.edu](apurba.pokharel@unt.edu)  \nRam Dantu  \nUniversity of North Texas [ram.dantu@unt.edu](ram.dantu@unt.edu)  \nShakila Zaman University of North Texas [shakila.zaman@unt.edu](shakila.zaman@unt.edu)  \nVinh Quach Sirisha Talapuru  \nUniversity of North Texas University of North Texas [vinh.quach@unt.edu](vinh.quach@unt.edu) [sirishamadh.talapuru@unt.edu](sirishamadh.talapuru@unt.edu)  \narXiv :2504 .02128v2 [ cs .MA] 8 Feb 2026  \nAbstract—Blockchain consensus mechanisms have relied on algorithms such as Proof-of-Work (PoW) and Proof-of-Stake (PoS) to ensure network functionality and integrity. However, these approaches struggle with adaptability for decision-making where the opinions of each matter rather than reaching an agreement based on honest majority or weighted consensus. This paper introduces a novel deliberation-based consensus mechanism where Large Language Models (LLMs) act as rational agents engaging in structured discussions to reach a unanimous consensus. By leveraging graded consensus and a multi-round deliberation process, our approach ensures unanimous consensus for definitive problems and graded consensus for prioritized decision problems and policies. We provide a formalization of our system and use it to show that the properties of blockchains are maintained, while also addressing the behavior in terms of adversaries, stalled deliberations, and confidence in consensus. Moreover, experimental results demonstrate system feasibility, showcasing convergence, block properties, and accuracy, which enable deliberative decision-making on blockchain networks. Index Terms—Blockchain, Consensus, Deliberation, LLMs.  \nI. INTRODUCTION AND MOTIVATION  \nAbsence of Deliberative Consensus in Blockchain:  \nBlockchains introduced a new way of processing financial transactions within a decentralized network, which guarantees that transactions are validated and recorded by the network through a consensus mechanism (e.g., PoW [1], PoS [2], etc.) . However, a key observation is made that the majority of the consensus protocols being used in blockchains are designed for cryptocurrencies [3] or financial applications [4], [5], [6] . Moreover, these protocols are primarily designed with an agreement quorum to handle the presence of faulty/malicious nodes. For instance, PoW considers a 51% majority, whereas PoS-BFT practices 33% adversary tolerance [7] . Although these kinds of agreements are advantageous when considering failure or malice, they cannot guarantee a reliable solution for high-stakes applications (e.g., court verdict systems, healthcare decisions, ethics committees, and government policy-making systems) that require unanimous consensus among all participants [8] . For instance, a jury should reflect a fair verdict by evaluating all committee members’ opinions through rounds of structured deliberation to prevent biased or unfair decisions [9] . In healthcare, decisions such as transitioning to human drug testing require strong or near-unanimous agreement, which is likewise impossible with current consensus mechanisms. Figure 1 represents the limitations of current consensus protocols.  \nFig. 1: Decision-making process of high-stake application requires active communication, argument processing to reach a unanimous outcome, and demands a structured deliberation framework. However, existing blockchain consensus protocols are limited in addressing such complex consensus problems and fail to support deliberation among participants.  \nContribution of Blockchain to Deliberation: Deliberation is used prevalently in robotics [10], governance [11], and Artificial Intelligence (AI) [12], highlighting its impact on improving decision-making performance. However, current deliberation implementations are limited in structured reasoning, argument verification, decision refinements, ensuring participation, and tra","cbCaie72raP1cxJW","https://ap.wps.com/l/cbCaie72raP1cxJW","pdf",1162278,2,1,7,"English","en",105,"# Abstract\n# Introduction and Motivation\n## Absence of Deliberative Consensus in Blockchain\n## Contribution of Blockchain to Deliberation\n# Problem Definition\n## High-stakes requirements for unanimous agreement\n## Deliberation and LLM-based consensus accuracy","[{\"question\":\"What properties and behaviors does the paper analyze for the proposed consensus?\",\"answer\":\"The paper formalizes the system to show that blockchain properties are maintained, while also evaluating behavior under adversaries, stalled deliberations, and the confidence level associated with consensus outcomes.\"}]",1784187695,18,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":78,"head_meta":80,"extra_data":82,"updated_unix":28},"achieving-unanimous-consensus-through-multi-agent-deliberation","",{"@graph":36,"@context":77},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,47,50],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":20},"https://docshare.wps.com/document/","Document",{"item":48,"name":12,"@type":43,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/achieving-unanimous-consensus-through-multi-agent-deliberation/83435/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-25","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71],{"name":72,"@type":73,"acceptedAnswer":74},"What properties and behaviors does the paper analyze for the proposed consensus?","Question",{"text":75,"@type":76},"The paper formalizes the system to show that blockchain properties are maintained, while also evaluating behavior under adversaries, stalled deliberations, and the confidence level associated with consensus outcomes.","Answer","https://schema.org",{"og:url":51,"og:type":79,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":81,"canonical":51},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":84},[85,89,93,97,102,107,111,114,119,122,126],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":86,"show_sort_weight":87,"slug":88},"Story & Novel",90,"story-novel",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":90,"show_sort_weight":91,"slug":92},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Exam",70,"exam",{"id":98,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},5,"Comic",60,"comic",{"id":103,"doc_module":4,"doc_module_name":46,"category_name":104,"show_sort_weight":105,"slug":106},6,"Technology",50,"technology",{"id":22,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":112,"slug":113},30,"research-report",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},9,"Religion & Spirituality",20,"religion-spirituality",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":120,"show_sort_weight":117,"slug":121},"World Cup","world-cup",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":123,"slug":125},10,"Lifestyle","lifestyle",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":98,"slug":129},19,"General","general"]