[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-86153-en":3,"doc-seo-86153-105":30,"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":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},86153,962075114101,"Seraphina","https://ap-avatar.wpscdn.com/avatar/e000253a75eb197efd?x-image-process=image/resize,m_fixed,w_180,h_180&k=1780044092746381165",8,"Research & Report","NextFund: A Unified Performance Tracking Platform for Agentic Portfolio Management","Large language model (LLM) agents increasingly participate in portfolio construction and market analysis, yet current evaluation practice is misaligned with real-time information and risk constraints. NEXTFUND introduces a unified evaluation platform that makes financial-agent behavior observable in live markets by pairing time-consistent market access, coordinated multi-agent analysis, and persistent end-to-end logging. An interactive Trading Arena supports cross-market benchmarking and inspection from leaderboard results down to individual justifications, demonstrated on HK, U.S., and China A-share equities.","NEXTFUND: A Unified Performance Tracking Platform  \nfor Agentic Portfolio Management  \nChanglun Li* Peixian Ma Qiqi Duan Zhenyu Lin Peineng Wu  \nParadoox AI Research  \narXiv :2607 . 1 1 14 1v 1 [ cs .AI] 13 Jul 2026  \nAbstract  \nLarge language models (LLMs) based agents are beginning to participate in portfolio construction and market analysis, where decisions must be justified under evolving information and risk constraints. Current assessment practice, however, remains poorly aligned with this setting: many studies rely on static examinations or report only terminal portfolio returns, while the intermediate evidence, analyst judgments, and execution steps that produced those returns stay largely invisible. We introduce NEXTFUND, an evaluation platform that makes financial-agent behavior observable under live market conditions. The platform couples time-consistent market access, coordinated multi-agent analysis, and persistent logging of the full decision path from observation to trade. Through an interactive Trading Arena, users can compare models across markets, inspect equity curves, and drill from leaderboard outcomes down to individual justifications. We present NEXTFUND on Hong Kong, U.S., and China A-share equities, illustrating how inspectable decision histories enable fairer benchmarking and more actionable diagnosis. Our demo is available at [https:](https:)//[paradoox.cn/nextfund/](paradoox.cn/nextfund/) .  \n1 Introduction  \nRecent advancement of large language models (LLMs) has driven a shift from static financial text analysis toward agentic portfolio management, where LLMs-based agents can plan, gather evidence, and act under live market conditions (Xiao et al., 2024 ; Li et al., 2025, 2024 ; Yu et al., 2023 ; Xiong et al., 2025 ; Fan et al., 2025 ; YANG et al., 2025) . Unlike traditional quantitative systems that follow fixed features and hard-coded rules, LLMbased agents can combine prices, news, calendars, and portfolio constraints through multi-step reasoning before placing an order. This change widens  \n* Correspondence: [tiger@paradoox.ai](tiger@paradoox.ai)  \nwhat financial automation can do, but it also raisesa crucial tracking question: can an agent’s portfolio decisions be shown to be reliable, comparable across models, and open to systematic improvement when markets move in real time?  \nExisting benchmarks answer this question only in part. Many focus on task coverage or final performance metrics such as cumulative return and Sharpe ratio, while giving little insight into how an action was formed (Li et al., 2024 ; Xiao et al., 2024 ; Fan et al., 2025) . As a result, users who need to approve, monitor, or improve agent strategies still face three recurring problems:  \nIncomplete Evaluation. Standard quizzes and generic leaderboards rarely test whether an agent can work with live market information, follow portfolio constraints, and stay stable across different market conditions.  \nOpaque Failure Diagnosis. When an agent uses unsupported evidence, mishandles tools, or drifts from its investment mandate, developers often cannot tell whether the fault lies in retrieval, analysis, synthesis, or execution, and thus cannot improve the system with clear, repeatable feedback.  \nLost Evaluation Traces. Decision logs, error cases, reviewer notes, and tool-call histories are often discarded after a run. Institutions therefore gain little reusable data for later prompt revision or model adaptation.  \nThese problems grow more serious in multi-step workflows. An early error in evidence selection or time alignment can lead to a costly portfolio change. Backtests that look only at final profit and loss therefore miss the failure modes that matter most for risk control and review. What is needed is a unified performance tracking platform where agentic portfolio decisions can be measured at each step, compared across models, and retained for later improvement.  \nWe present NEXTFUND, a unified performance tracking platf","cbCaiqvHuNPCFAYP","https://ap.wps.com/l/cbCaiqvHuNPCFAYP","pdf",1245080,4,1,10,"English","en",105,"# Introduction\n## Evaluation gaps in existing benchmarks\n## NEXTFUND overview and comparison","[{\"question\":\"What evaluation gaps does NEXTFUND target in current agentic portfolio research?\",\"answer\":\"It addresses incomplete evaluation of live market capability under constraints, opaque failure diagnosis across evidence, analysis, synthesis, and execution, and lost evaluation traces where decision logs and tool histories are discarded after runs.\"},{\"question\":\"How does NEXTFUND make an agent’s decisions observable during live trading?\",\"answer\":\"NEXTFUND records a full decision path—from observations to analyst outputs and executed trades—using persistent end-to-end logging under a shared, synchronized point-in-time market view.\"},{\"question\":\"What does the Trading Arena enable for comparing and inspecting models?\",\"answer\":\"The interface provides cross-market leaderboards and step-wise inspection so users can drill from performance differences to underlying agent behaviors and individual justifications rather than relying only on terminal returns.\"}]",1784208954,25,{"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":86,"head_meta":88,"extra_data":90,"updated_unix":28},"nextfund-a-unified-performance-tracking-platform-for-agentic-portfolio-management","",{"@graph":36,"@context":85},[37,53,68],{"@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":20},"https://docshare.wps.com/document/nextfund-a-unified-performance-tracking-platform-for-agentic-portfolio-management/86153/",{"url":52,"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",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What evaluation gaps does NEXTFUND target in current agentic portfolio research?","Question",{"text":75,"@type":76},"It addresses incomplete evaluation of live market capability under constraints, opaque failure diagnosis across evidence, analysis, synthesis, and execution, and lost evaluation traces where decision logs and tool histories are discarded after runs.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does NEXTFUND make an agent’s decisions observable during live trading?",{"text":80,"@type":76},"NEXTFUND records a full decision path—from observations to analyst outputs and executed trades—using persistent end-to-end logging under a shared, synchronized point-in-time market view.",{"name":82,"@type":73,"acceptedAnswer":83},"What does the Trading Arena enable for comparing and inspecting models?",{"text":84,"@type":76},"The interface provides cross-market leaderboards and step-wise inspection so users can drill from performance differences to underlying agent behaviors and individual justifications rather than relying only on terminal returns.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,134],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"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":22,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":22,"slug":133},"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]