[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-273527-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-273527-en":131},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":74,"head_meta":76,"extra_data":78,"updated_unix":80},105,"en","arbormem-navigating-interaction-states-with-memory-forests-online-memory-framework","ArborMem - Navigating Interaction States with Memory Forests - Online Memory Framework","","Large language models are increasingly used as persistent conversational assistants, demanding memory that keeps relevant experience and continuity across long-term interactions. Many existing methods improve access to history via long-context modeling, selective retrieval, and structured memory stores, yet often fail to identify which prior interaction state a user’s current turn resumes. ArborMem represents ongoing dialogue as a navigable forest of interaction-state branches. It localizes the resumed state, restores branch-local context, and augments with reusable evidence from other branches to avoid conflating distinct trajectories. ArborMem and BranchMemEval show strong gains under constrained read budgets.",{"@graph":14,"@context":73},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/research-report/","Research & Report",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/arbormem-navigating-interaction-states-with-memory-forests-online-memory-framework/273527/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/arbormem-navigating-interaction-states-with-memory-forests-online-memory-framework/273527.png","ImageObject",300,407,{"name":42,"@type":43},"Hazel","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-11-06","2026-09-15",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",15,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"What problem does ArborMem address in long-running conversations?","Question",{"text":63,"@type":64},"Most systems retrieve relevant past information but do not determine which prior interaction state the current turn resumes, causing confusion when conversations interleave multiple tasks. ArborMem focuses on preserving continuity across structurally distinct trajectories.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"How does ArborMem represent conversation memory?",{"text":68,"@type":64},"It models a long-running conversation as a navigable forest of interaction states. Each branch keeps a locally coherent trajectory that can later be resumed.",{"name":70,"@type":61,"acceptedAnswer":71},"What is BranchMemEval and why is it introduced?",{"text":72,"@type":64},"BranchMemEval is a controlled diagnostic benchmark for interleaved and resumable interaction trajectories. It fills the gap where existing long-term memory benchmarks do not explicitly isolate branch-structured challenges.","https://schema.org",{"og:url":32,"og:type":75,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":77,"canonical":32},"index,follow",{"doc_id":79,"site_id":7},273527,1789471890,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,106,111,115,120,123,127],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":85,"show_sort_weight":86,"slug":87},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":89,"show_sort_weight":90,"slug":91},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":93,"show_sort_weight":94,"slug":95},"Exam",70,"exam",{"id":97,"doc_module":4,"doc_module_name":25,"category_name":98,"show_sort_weight":99,"slug":100},5,"Comic",60,"comic",{"id":102,"doc_module":4,"doc_module_name":25,"category_name":103,"show_sort_weight":104,"slug":105},6,"Technology",50,"technology",{"id":107,"doc_module":4,"doc_module_name":25,"category_name":108,"show_sort_weight":109,"slug":110},7,"Healthcare",40,"healthcare",{"id":112,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":113,"slug":114},8,30,"research-report",{"id":116,"doc_module":4,"doc_module_name":25,"category_name":117,"show_sort_weight":118,"slug":119},9,"Religion & Spirituality",20,"religion-spirituality",{"id":118,"doc_module":4,"doc_module_name":25,"category_name":121,"show_sort_weight":118,"slug":122},"World Cup","world-cup",{"id":124,"doc_module":4,"doc_module_name":25,"category_name":125,"show_sort_weight":124,"slug":126},10,"Lifestyle","lifestyle",{"id":128,"doc_module":4,"doc_module_name":25,"category_name":129,"show_sort_weight":97,"slug":130},19,"General","general",{"code":4,"msg":82,"data":132},{"doc_id":79,"user_id":133,"nickname":42,"user_avatar":134,"doc_module":4,"category_id":112,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":140,"language":141,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":142,"faqs":143,"seo_title":144,"seo_description":12,"update_tm":80,"read_time":99,"preview_page_count":4},137441390410,"https://ap-avatar.wpscdn.com/avatar/2000252f4ab5702993?_k=1776741390130283984","ArborMem: Navigating Interaction States with Memory Forests  \nZongwei Lv 1∗, Yuemeng Xu 1∗, Yilun Yao 1∗, Dingsiyi 1∗, Xinyu Tan2 , Yaoming Li 1 , Guangxiang Zhao3 , Weihong Lin4 , Lin Sun4 , Xiangzheng Zhang4 , Tong Yang 1†  \n1Peking University  \n2Beijing University of Posts and Telecommunications  \n3 Qiyuan Tech  \n4 Qihoo 360  \narXiv : 2608 . 17534v 1 [cs .CL] 18 Aug 2026  \nAbstract  \nLarge language models increasingly serve as persistent conversational assistants, requiring memory that preserves relevant experience and maintains continuity across interactions. Existing methods improve access to conversational history through long-context processing, selective retrieval, and structured memory organization. However, most systems treat memory access as retrieving relevant past information without first determining which prior interaction state the current turn resumes. This limitation becomes particularly important when conversations interleave multiple tasks, people, and plans that may be interrupted and later revisited. We introduce ArborMem, an online memory framework that represents along-running conversation as a navigable forest of interaction states. Each branch preserves a locally coherent trajectory, while the forest maintains multiple trajectories that may later be resumed. For each new input, ArborMem localizes the relevant state, restores its branch-local context, and augments it with reusable evidence retrieved across branches, preserving interaction continuity without conflating semantically related but structurally distinct trajectories. Existing long-term memory benchmarks cover diverse memory and reasoning capabilities but do not explicitly isolate branch-structured challenges. We therefore introduce BranchMemEval, a controlled diagnostic benchmark for interleaved and resumable interaction trajectories. Experiments on LongMemEval, LoCoMo, BEAM 100K, and BranchMemEval show that ArborMem outperforms the strongest baselines by 3.36–10.31 percentage points on the three established benchmarks and by 5.0 points on BranchMemEval. Its advantage grows under constrained read budgets, while complete memory queries remain below half a second.  \nIntroduction  \nLarge language models increasingly serve as persistent conversational assistants rather than one-shot questionanswering systems. As interactions extend over days or weeks, users expect assistantstoremember prior discussions, track ongoing tasks, and resume earlier plans. Yet a language model has no durable state beyond the information available  \n∗The first four authors contributed equally; their ordering was randomized.  \n†Corresponding author.  \nCopyright © 2027, Association for the Advancement of Artificial Intelligence ([www.aaai.org](www.aaai.org)). All rights reserved.  \n1 Sam is revising his paper.  \nFigure 1: A motivating example of interaction-state localization. Although the most recent turns concern Sam’s conference trip, the underspecified follow-up resumes the earlier paper-revision trajectory.  \nin its current context. Long-running conversational agents therefore require memory that preserves relevant experience and maintains continuity as users’ needs evolve (Maharana et al. 2024) .  \nExisting methods improve access to conversational history in several ways. Long-context models expose more history directly, with recent frontier models supporting context windows on the order of one million tokens (Gemini Team et al. 2024) . However, context windows remain bounded, and making information visible does not ensure that it will be identified and used reliably (Liu et al. 2024) . Selective memory systems instead externalize history as retrieved passages, summaries, episodic records, or extracted facts, as in Generative Agents (Park et al. 2023), MemoryBank (Zhong et al. 2024), and Mem0 (Chhikara et al. 2025) . Other methods organize memory through hierarchical stores, linked notes, trees, or temporal knowledge graphs, including MemGPT (Packer et al. 2024), A-","cbCaibok6223zjJ4","https://ap.wps.com/l/cbCaibok6223zjJ4","pdf",1625582,24,"English","# Abstract\n# Introduction","[{\"question\":\"What problem does ArborMem address in long-running conversations?\",\"answer\":\"Most systems retrieve relevant past information but do not determine which prior interaction state the current turn resumes, causing confusion when conversations interleave multiple tasks. ArborMem focuses on preserving continuity across structurally distinct trajectories.\"},{\"question\":\"How does ArborMem represent conversation memory?\",\"answer\":\"It models a long-running conversation as a navigable forest of interaction states. Each branch keeps a locally coherent trajectory that can later be resumed.\"},{\"question\":\"What is BranchMemEval and why is it introduced?\",\"answer\":\"BranchMemEval is a controlled diagnostic benchmark for interleaved and resumable interaction trajectories. It fills the gap where existing long-term memory benchmarks do not explicitly isolate branch-structured challenges.\"}]","ArborMem - Navigating Interaction States with Memory Forests - Online Memory Framework | PDF"]