[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-327648-105":59,"doc-detail-327648-en":131},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":124,"head_meta":126,"extra_data":128,"updated_unix":130},105,"en","beyond-forecasting-the-belief-to-trade-layer-in-prediction-market-agents","Beyond Forecasting - The Belief-to-Trade Layer in Prediction-Market Agents","","Forecasting future events serves as a general-purpose AI evaluation testbed, but trading-based evaluation requires more than accurate probability estimates. Existing benchmarks show a persistent gap between calibrated probability scores and realized trading returns because trading rules are treated as fixed protocols and risk controls are rarely treated as designable components. This work introduces Raven-Agent, an autonomous prediction-market trading agent with an explicit deterministic composable trading layer, validated via controlled replay on an archived decision set and achieving positive return and positive risk-adjusted return among tested policies.",{"@graph":69,"@context":123},[70,84,106],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/beyond-forecasting-the-belief-to-trade-layer-in-prediction-market-agents/327648/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/beyond-forecasting-the-belief-to-trade-layer-in-prediction-market-agents/327648.png","ImageObject",300,407,{"name":92,"@type":93},"Noah","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-13","2026-09-21",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",11,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"Why does calibrated probability not guarantee profitable prediction-market trades?","Question",{"text":113,"@type":114},"Benchmarks report a gap between calibrated probability scores and trading results. Strong probability scores may fail to translate into profitable trades because downstream trading rules and risk control are often fixed or missing rather than designed as explicit modules.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"What is Raven-Agent in this paper?",{"text":118,"@type":114},"Raven-Agent is presented as the first autonomous trading agent for prediction markets, built around an explicit deterministic composable trading layer. It separates selection, sizing, and risk control from the forecasting component.",{"name":120,"@type":111,"acceptedAnswer":121},"How does the proposed trading layer make trading decisions?",{"text":122,"@type":114},"The layer includes a ranking module using a time-normalized return score, a sizing module using a fractional Kelly bet, and an execution and risk module enforcing deterministic constraints such as stake, exposure, stop loss, and drawdown outside the model prompt.","https://schema.org",{"og:url":83,"og:type":125,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":127,"canonical":83},"index,follow",{"doc_id":129,"site_id":62},327648,1790467078,{"code":4,"msg":5,"data":132},{"doc_id":129,"user_id":133,"nickname":92,"user_avatar":134,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":105,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":52,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":144,"read_time":145,"preview_page_count":4},8796095462418,"https://ap-avatar.wpscdn.com/avatar/80000253c1241d02b47?x-image-process=image/resize,m_fixed,w_180,h_180&k=1778826106357471780","Beyond Forecasting: The Belief-to-Trade Layer in Prediction-Market Agents  \nYishu Wang 1 Yuxuan Wang 2 Jiaqi Deng 3 Hanyang Tang 4  \narXiv :2607 .030 15v 1 [ cs .AI] 3 Jul 2026  \nAbstract  \nForecasting future events has attracted growing attention as a testbed for general-purpose AI. A natural way to ground this evaluation is let the models trade in the prediction markets. Trading, however, requires more than forecasting. Moreover, recent benchmarks report a substantial gap between calibrated probability scores and the trading results. We propose Raven-Agent, to the best of our knowledge, the first autonomous trading agent for prediction markets. On a controlled replay over an archived decision set, our architecture achieves the only positive return and the only positive risk-adjusted return among all tested policies. We have released our code in [https://github.com/Alchemist-X/predict-raven](https://github.com/Alchemist-X/predict-raven).  \n1. Introduction  \nForecasting future events has attracted growing attention as a testbed for general-purpose AI (Karger et al., 2024 ; Yang et al., 2025) . The task demands retrieval, temporal reasoning, and decision under uncertainty. It is naturally studied as a joint problem of probability estimation and action under that estimate.  \nTo make progress on this problem, one line of exisiting works focuses on probability quality and improves LLM forecasters on resolved events. The Belief-Logit-Forecaster (BLF) of Murphy (2026) uses structured belief states and multi-trial aggregation, currently leading ForecastBench (Karger et al., 2024) . Yet such systems improve calibration without acting on their forecasts. On the other hand, prediction market benchmarks score systems by realized trading return as well as by probability (Yang et al., 2025 ; Cheng et al., 2026 ; Zhang et al., 2026) . They consistently  \n1Hong Kong University of Science and Technology 2Peking University 3The University of Hong Kong 4Massachusetts Institute of Technology.  \nCorrespondence to: Yishu Wang \u003C[issue.00.gui@gmail.com](issue.00.gui@gmail.com) >,  \nYuxuan Wang \u003C[yuxwang@pku.edu.cn](yuxwang@pku.edu.cn) >, Jiaqi Deng \u003Cjiaqideng@connect.hku.hk>, Hanyang Tang \u003C[hytangs@mit.edu](hytangs@mit.edu) >.  \nICML 2026 Workshop on AI Forecasting, Seoul, South Korea, 2026.  \nreport that strong probability scores do not translate into profitable trades. However, they treat the trading rule asa fixed protocol such as a per market bet or a confidence threshold, not as a designable object. Moreover, position sizing, portfolio exposure, and risk control are either absent or expressed as a prompt instruction in these papers. We refer to these downstream components as the trading layer, and we make it the object of study in this paper.  \nAcross both lines, the trading layer is either omitted or hardcoded, never treated as a designable object. A useful trading layer should be explicit and modular, with selection, sizing, and risk control as separate components. It should be deterministic, so that risk constraints remain in effect even when the model is confidently wrong. It should also be composable with any forecaster, so that improvements in calibration and in trade execution can be evaluated independently.  \nIn this paper, we propose Raven-Agent, an autonomous prediction market agent built around an explicit, deterministic, composable trading layer. Within the layer, a ranking module addresses selection by scoring each candidate by a time normalized return rate. The same module addresses sizing with a fractional Kelly bet on the retained positions. An execution and risk module addresses risk control by enforcing deterministic constraints on stake, exposure, stop loss, and drawdown outside the language model prompt. We also include an information module for evidence retrieval and a forecasting module that produces per contract probabilities. We validate Raven-Agent on a controlled replay protocol. The results show our method improves re","cbCaiiVDSlkR0ENr","https://ap.wps.com/l/cbCaiiVDSlkR0ENr","pdf",871873,"English","# Abstract\n# 1. Introduction\n# 2. Problem Setup\n## 2.1. Prediction Markets\n## 2.2. Trading policies","[{\"question\":\"Why does calibrated probability not guarantee profitable prediction-market trades?\",\"answer\":\"Benchmarks report a gap between calibrated probability scores and trading results. Strong probability scores may fail to translate into profitable trades because downstream trading rules and risk control are often fixed or missing rather than designed as explicit modules.\"},{\"question\":\"What is Raven-Agent in this paper?\",\"answer\":\"Raven-Agent is presented as the first autonomous trading agent for prediction markets, built around an explicit deterministic composable trading layer. It separates selection, sizing, and risk control from the forecasting component.\"},{\"question\":\"How does the proposed trading layer make trading decisions?\",\"answer\":\"The layer includes a ranking module using a time-normalized return score, a sizing module using a fractional Kelly bet, and an execution and risk module enforcing deterministic constraints such as stake, exposure, stop loss, and drawdown outside the model prompt.\"}]","Beyond Forecasting - The Belief-to-Trade Layer in Prediction-Market Agents | PDF",1789977723,25]