[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-84016-en":3,"doc-seo-84016-105":30,"detail-sidebar-cat-0-en-105":92},{"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},84016,7971461740909,"Levi","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","StateFuse Deterministic Conflict-Preserving Memory for Multi-Agent Systems","Agent systems accumulate conflicting observations across branches, retries, and replicas, yet many practical memory layers hide disagreement via hard overwrite rules that are hard to inspect or fix. StateFuse introduces a conflict-aware replicated memory contract that keeps immutable history and explicit conflict objects on top of standard OpSet/CRDT merging. It offers targeted correction handles (claim id/claim ref), deterministic predicate contracts, and projection-time resolution that cannot rewrite replicated state. Evaluations show conflict-preserving surfaces improve contradiction visibility and enable safer abstention and auditable correction under matched policies.","StateFuse: Deterministic Conflict-Preserving Memory for  \nMulti-Agent Systems  \nSergey Volkov The University of Hong Kong  \nsavolkov@hku .hk  \nYang Li The University of Hong Kong  \nyli9919@hku .hk  \narXiv :2607 .05844v 1 [ cs .AI ] 7 Jul 2026  \nYe Luo  \nThe University of Hong Kong  \nkurtluo@hku .hk  \nAbstract  \nAgent systems accumulate conflicting observations across branches, retries, and replicas, yet many practical memory layers still collapse disagreement behind overwrite rules that are difficult to inspect or correct. We present StateFuse, a conflict-aware replicated memory contract built on standard OpSet/CRDT merge. StateFuse does not introduce a new join algebra; it defines an agent-facing semantics layer with immutable history, explicit conflict objects, exact and semantic correction handles (claim   id / claim   ref), deterministic predicate contracts, and projection-time resolution that cannot rewrite replicated state.  \nWe evaluate StateFuse against flat multi-value, raw-log, provenance-style, and collapsed baselines under matched resolver and verification policies. On a 282-question official conflict-bearing MemoryAgentBench slice, the compared methods tie on answer accuracy, but conflict-preserving surfaces keep contradictions visible while collapsed surfaces do not. In a controlled agent loop with uniform verification, preserving ambiguity enables safer abstention and correction than early collapse. A correction-handle ablation further shows that semantic handles matter when exact prior identifiers are unavailable.  \nThe resulting claim is narrow: StateFuse is best supported as a safer public memory contract for contradiction surfacing, abstention, and auditable correction, not as a universal accuracy gain.  \nKeywords: agent memory; CRDT; OpSet; conflict resolution; replicated data  \nCode and supplementary materials: [https://github.com/nZiben/statefuse](https://github.com/nZiben/statefuse)  \n1 Introduction  \nAgent systems increasingly operate as branching, tool-using, distributed processes. They speculate, retry, fork into subplans, and later reconcile what each branch believes. In this setting, memory is not only a retrieval problem but also a correction and merge semantics problem: when two branches assert incompatible facts about the same entity, should the system overwrite one value, preserve both, retract one explicitly, or defer the choice to task-local policy? Many practical memory stacks leave this question implicit. The result is a familiar cluster of failures: hidden overwrite of branch disagreement, stale observations surviving validated corrections, and unsafe actions taken from collapsed memory surfaces.  \nDistributed systems already provide the right convergence substrate. CRDT joins and OpSet-style interpretations show how replicas can exchange immutable updates and recover equivalent state through associative, commutative, and idempotent merge [1, 5, 6, 15] . StateFuse does not propose a new join. Its  \nfocus is the contract that sits on top of that substrate for agent memory: what the replicated history stores, what a public projection must expose, how corrections are targeted, and what downstream policies are allowed to decide.  \nWe make two design choices in the evaluation. First, we narrow the empirical claim. We do not argue that explicit conflict objects universally beat strong flat multi-value surfaces on answer accuracy. Instead, we argue that StateFuse provides a stronger public memory contract for contradiction surfacing, abstention, and auditable correction. Second, we make the main comparisons fairer. Flat multi-value and raw-log baselinesnow receive conservative variants from the same resolver family, and the downstream agent loop gives every method the same verification budget.  \nThe StateFuse contract has five main components:  \n1. Immutable replicated history for evidence, claims, retractions, and decisions.  \n2. Explicit public conflict surfacing at projection time rather than s","cbCaiitd2J1LdXUB","https://ap.wps.com/l/cbCaiitd2J1LdXUB","pdf",192059,5,1,18,"English","en",105,"# Introduction\n## Problem: conflicting observations in agent branching\n## Background: CRDT and OpSet-style convergence substrate\n## Evaluation design and narrowed claim\n## StateFuse contract components\n# Experimental results\n## MemoryAgentBench slice accuracy and conflict visibility\n## Controlled agent loop: abstention and correction","[{\"question\":\"What problem does StateFuse address in multi-agent systems?\",\"answer\":\"StateFuse targets the difficulty of handling conflicting observations across branching, retries, and replicas, where many memory layers silently overwrite disagreement and make it hard to audit or correct. It aims to preserve contradiction visibility instead of collapsing it automatically.\"},{\"question\":\"How does StateFuse preserve conflicts while using CRDT/OpSet-style replication?\",\"answer\":\"StateFuse builds on standard OpSet/CRDT merge but adds an agent-facing semantics layer. It maintains immutable replicated history, exposes explicit conflict objects during projection time, and prevents resolvers from rewriting replicated state.\"},{\"question\":\"What are the main takeaways from the evaluation of StateFuse?\",\"answer\":\"On a conflict-bearing MemoryAgentBench slice, StateFuse ties with strong flat conflict-preserving baselines on answer accuracy, while collapsed or raw-log surfaces do not. Under uniform verification in a controlled agent loop, preserving ambiguity supports safer abstention and correction, and ablations show semantic correction handles matter when exact identifiers are unavailable.\"}]",1784192030,45,{"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":87,"head_meta":89,"extra_data":91,"updated_unix":28},"statefuse-deterministic-conflict-preserving-memory-for-multi-agent-systems","",{"@graph":36,"@context":86},[37,54,69],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/statefuse-deterministic-conflict-preserving-memory-for-multi-agent-systems/84016/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-07-27","2026-07-16",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What problem does StateFuse address in multi-agent systems?","Question",{"text":76,"@type":77},"StateFuse targets the difficulty of handling conflicting observations across branching, retries, and replicas, where many memory layers silently overwrite disagreement and make it hard to audit or correct. It aims to preserve contradiction visibility instead of collapsing it automatically.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How does StateFuse preserve conflicts while using CRDT/OpSet-style replication?",{"text":81,"@type":77},"StateFuse builds on standard OpSet/CRDT merge but adds an agent-facing semantics layer. It maintains immutable replicated history, exposes explicit conflict objects during projection time, and prevents resolvers from rewriting replicated state.",{"name":83,"@type":74,"acceptedAnswer":84},"What are the main takeaways from the evaluation of StateFuse?",{"text":85,"@type":77},"On a conflict-bearing MemoryAgentBench slice, StateFuse ties with strong flat conflict-preserving baselines on answer accuracy, while collapsed or raw-log surfaces do not. Under uniform verification in a controlled agent loop, preserving ambiguity supports safer abstention and correction, and ablations show semantic correction handles matter when exact identifiers are unavailable.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,110,115,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":20,"slug":138},19,"General","general"]