[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-85873-en":3,"doc-seo-85873-105":29,"detail-sidebar-cat-0-en-105":90},{"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":4,"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},85873,1099514068035,"Ezra","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Can Agentic Trading Systems Pay for Their Own Intelligence","Large language model (LLM) agents are increasingly deployed in trading systems, where reasoning, tool use, and continual decision-making introduce costs that should be recovered as incremental trading value. Existing evaluations often report performance metrics but seldom test agentic viability—whether induced costs are converted into measurable profit. The document proposes TradeLens, a trace-grounded diagnostic toolkit that reconstructs trading trajectories, attributes profit and cost to interpretable evidence, and diagnoses intelligence-to-profit conversion failures across models, scales, frequencies, and architectures.","Can Agentic Trading Systems Pay for Their Own Intelligence?  \nQiqi Duan1∗, Changlun Li2∗, Chen Wang1∗, Fan Zhang4,5 , Mengxiang Wang1 , Dayi Miao1 , Peixian Ma2 , Jiangpeng Yan3 , Liyuan Chen3 , Shuoling Liu3 , Preslav Nakov4 , Yuyu Luo 1,2 , Nan Tang 1,2†  \n1HKUST(GZ) 2Paradoox AI 3E Fund Management Co., Ltd 4MBZUAI 5The University of Tokyo  \n∗ Equal contribution. † Corresponding author: [nantang@hkust-gz.edu.cn](nantang@hkust-gz.edu.cn)  \narXiv :2607 . 10286v 1 [ cs .AI] 11 Jul 2026  \nAbstract  \nLarge language model (LLM) agents are increasingly used in trading systems, where model reasoning, tool use, and continual decisions incur costs that are expected to produce trading value. Existing evaluations typically report performance metrics, but rarely examine agentic viability: whether dynamic LLM-mediated decisions convert their induced costs into measurable incremental profit. To apply this criterion, we introduce TradeLens, a trace-grounded diagnostic toolkit for evaluating agentic trading systems from their trading records, runtime traces, and deployment configurations. It reconstructs trading trajectories, attributes profit and cost to interpretable evidence, and diagnoses whether and why an agent pays for its own intelligence. We conduct extensive analysis across backbone models, capital scales, trading frequencies, and system architectures, together with deployment discussion. Our results show that viability hingeson intelligence-to-profit conversion: models exhibit different failure patterns, such as poor asset selection in DeepSeek-V3.2 and negative timing in GLM-4.7, while capital scale, trading frequency, and architecture matter only by amplifying or degrading decision-attributed timing value. These findings reframe the evaluation of LLM-based trading agents from capabilitycentric performance ranking to trace-grounded diagnosis of intelligence-to-profit conversion. Our code is available at [https://anonymous](https://anonymous). [4open.science/r/TradeLens](4open.science/r/TradeLens).  \n1 Introduction  \nWith strong general reasoning abilities (Yu et al., 2023a ; Liu et al., 2023a ; Suma and Dauncey, 2025) and increasing adaptation to financial tasks (Wu et al., 2023 ; Chen et al., 2025a ; Liu et al., 2023b), LLM agents are moving from financial question answering to direct participation in trading workflows. Recent systems use LLMs as trading copilots (Fan et al., 2025 ; Yang et al., 2024), portfolio  \nFigure 1: Motivation. A profitable agentic trading system may still fail to create useful trading value, and diagnosing “Why” is challenging because both returns and costs arise from intertwined deployment drivers.  \nmanagers (Zhao et al., 2025 ; Ko and Lee, 2024), and market-analysis agents equipped with external tools (Han et al., 2025) .  \nObservation. Despite promising results, a critical gap remains in how agentic trading systems are evaluated. Most existing studies report gross profit or metrics such as Sharpe ratio (Li et al., 2025b ; Chen et al., 2025b ; Xie et al., 2023 ; Sharpe, 1994) . While useful for measuring trading performance, these metrics are incomplete for deployment: developers must assess not only how much profit a system makes, but also where the profit comes from and how deployment costs affect the realized margin. This concern echoes recent cost-aware LLM evaluation, which accounts for monetary output cost and inefficient reasoning computation (Erolet al., 2025 ; Zellinger and Thomson, 2025 ; Wanget al., 2025b ; Zhang et al., 2024) . In agentic trading, however, cost has a stricter meaning: it is the price paid for LLM-mediated intelligence, including model reasoning, tool use, memory retrieval,  \nand continual decision-making. Beyond operating within a budget (Wang et al., 2024), the system should also meet the token-economy requirement (Chen et al., 2026): generating enough incremental profit to justify the intelligence consumed by its trading decisions.  \nThe blind spot. This requirement cre","cbCail6kvGC4LbnL","https://ap.wps.com/l/cbCail6kvGC4LbnL","pdf",2845499,1,19,"English","en",105,"# Introduction\n## Motivation and gap in current evaluation\n## Blind spot in profit vs. cost\n## Goal: diagnose intelligence-to-profit conversion\n# TradeLens\n## Trace-grounded diagnostic toolkit","[{\"question\":\"What problem do the authors identify with current evaluations of agentic trading systems?\",\"answer\":\"Most studies focus on gross profit or metrics like Sharpe ratio but do not evaluate whether the system’s induced reasoning and deployment costs are converted into incremental trading value.\"},{\"question\":\"What is TradeLens, and what does it do?\",\"answer\":\"TradeLens is a trace-grounded toolkit that reconstructs trading trajectories and attributes profit and costs to interpretable evidence from trading records, runtime traces, and deployment configurations.\"},{\"question\":\"How do the authors define “agentic viability” in trading?\",\"answer\":\"Agentic viability means that LLM-mediated decisions generate enough incremental profit to justify the intelligence consumed by reasoning, tool use, memory retrieval, and continual decision-making.\"}]",1784206855,48,{"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":85,"head_meta":87,"extra_data":89,"updated_unix":27},"can-agentic-trading-systems-pay-for-their-own-intelligence","",{"@graph":35,"@context":84},[36,53,67],{"@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/can-agentic-trading-systems-pay-for-their-own-intelligence/85873/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-16",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"What problem do the authors identify with current evaluations of agentic trading systems?","Question",{"text":74,"@type":75},"Most studies focus on gross profit or metrics like Sharpe ratio but do not evaluate whether the system’s induced reasoning and deployment costs are converted into incremental trading value.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"What is TradeLens, and what does it do?",{"text":79,"@type":75},"TradeLens is a trace-grounded toolkit that reconstructs trading trajectories and attributes profit and costs to interpretable evidence from trading records, runtime traces, and deployment configurations.",{"name":81,"@type":72,"acceptedAnswer":82},"How do the authors define “agentic viability” in trading?",{"text":83,"@type":75},"Agentic viability means that LLM-mediated decisions generate enough incremental profit to justify the intelligence consumed by reasoning, tool use, memory retrieval, and continual decision-making.","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":45,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":21,"doc_module":4,"doc_module_name":45,"category_name":135,"show_sort_weight":105,"slug":136},"General","general"]