Deprecated: The each() function is deprecated. This message will be suppressed on further calls in /home/zhenxiangba/zhenxiangba.com/public_html/phproxy-improved-master/index.php on line 456 Paper page - TwinMarket: A Scalable Behavioral and Social Simulation for Financial
Markets
\n","updatedAt":"2025-02-06T02:54:59.097Z","author":{"_id":"643c047326f177a3e41627b6","avatarUrl":"/avatars/ade75cebd049daf080ba80a80d516240.svg","fullname":"Yifei Zhang","name":"amstrongzyf","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":1,"isUserFollowing":false}},"numEdits":1,"identifiedLanguage":{"language":"en","probability":0.3129032552242279},"editors":["amstrongzyf"],"editorAvatarUrls":["/avatars/ade75cebd049daf080ba80a80d516240.svg"],"reactions":[{"reaction":"👀","users":["amstrongzyf","Xidong","TobyYang7"],"count":3}],"isReport":false}},{"id":"67a56321166721c8f99044b3","author":{"_id":"63d3e0e8ff1384ce6c5dd17d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg","fullname":"Librarian Bot (Bot)","name":"librarian-bot","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":318,"isUserFollowing":false},"createdAt":"2025-02-07T01:34:25.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"This is an automated message from the [Librarian Bot](https://huggingface.co/librarian-bots). I found the following papers similar to this paper. \n\nThe following papers were recommended by the Semantic Scholar API \n\n* [Casevo: A Cognitive Agents and Social Evolution Simulator](https://huggingface.co/papers/2412.19498) (2024)\n* [Investigating Tax Evasion Emergence Using Dual Large Language Model and Deep Reinforcement Learning Powered Agent-based Simulation](https://huggingface.co/papers/2501.18177) (2025)\n* [Modeling Speculative Trading Patterns in Token Markets: An Agent-Based Analysis with TokenLab](https://huggingface.co/papers/2412.07512) (2024)\n* [Welfare Modeling with AI as Economic Agents: A Game-Theoretic and Behavioral Approach](https://huggingface.co/papers/2501.15317) (2025)\n* [How Different AI Chatbots Behave? Benchmarking Large Language Models in Behavioral Economics Games](https://huggingface.co/papers/2412.12362) (2024)\n* [Generative Emergent Communication: Large Language Model is a Collective World Model](https://huggingface.co/papers/2501.00226) (2024)\n* [Social Processes: Probabilistic Meta-learning for Adaptive Multiparty Interaction Forecasting](https://huggingface.co/papers/2501.01915) (2025)\n\n\n Please give a thumbs up to this comment if you found it helpful!\n\n If you want recommendations for any Paper on Hugging Face checkout [this](https://huggingface.co/spaces/librarian-bots/recommend_similar_papers) Space\n\n You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: `@librarian-bot recommend`","html":"
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
\n
The following papers were recommended by the Semantic Scholar API
Please give a thumbs up to this comment if you found it helpful!
\n
If you want recommendations for any Paper on Hugging Face checkout this Space
\n
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: \n\n@librarian-bot\n\t recommend
\n","updatedAt":"2025-02-07T01:34:25.630Z","author":{"_id":"63d3e0e8ff1384ce6c5dd17d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg","fullname":"Librarian Bot (Bot)","name":"librarian-bot","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":318,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.7424005270004272},"editors":["librarian-bot"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2502.01506","authors":[{"_id":"67a4214f12b90b15dc5a648e","user":{"_id":"63f622c69cbd6730302783eb","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/63f622c69cbd6730302783eb/9cb96JVKiOm_JhF-shbFw.jpeg","isPro":false,"fullname":"Yuzhe Yang","user":"TobyYang7","type":"user"},"name":"Yuzhe Yang","status":"claimed_verified","statusLastChangedAt":"2025-02-06T14:15:03.582Z","hidden":false},{"_id":"67a4214f12b90b15dc5a648f","user":{"_id":"643c047326f177a3e41627b6","avatarUrl":"/avatars/ade75cebd049daf080ba80a80d516240.svg","isPro":false,"fullname":"Yifei Zhang","user":"amstrongzyf","type":"user"},"name":"Yifei Zhang","status":"claimed_verified","statusLastChangedAt":"2025-02-06T14:15:05.578Z","hidden":false},{"_id":"67a4214f12b90b15dc5a6490","user":{"_id":"65fbdbc8fc9132a2dfd67c8f","avatarUrl":"/avatars/9e404fca5f7b53d49e1aa73d525f834d.svg","isPro":false,"fullname":"Minghao Wu","user":"magicc0nch","type":"user"},"name":"Minghao Wu","status":"claimed_verified","statusLastChangedAt":"2025-06-09T10:14:39.422Z","hidden":false},{"_id":"67a4214f12b90b15dc5a6491","name":"Kaidi Zhang","hidden":false},{"_id":"67a4214f12b90b15dc5a6492","user":{"_id":"67aafd473b9cb77cc2223819","avatarUrl":"/avatars/e285666fdc918564071be26136fe3312.svg","isPro":false,"fullname":"Yunmiao Zhang","user":"Yunwater","type":"user"},"name":"Yunmiao Zhang","status":"claimed_verified","statusLastChangedAt":"2025-02-11T10:03:21.159Z","hidden":false},{"_id":"67a4214f12b90b15dc5a6493","name":"Honghai Yu","hidden":false},{"_id":"67a4214f12b90b15dc5a6494","name":"Yan Hu","hidden":false},{"_id":"67a4214f12b90b15dc5a6495","user":{"_id":"637c6703ca8542a0ba900ccb","avatarUrl":"/avatars/288ed63a1efa566c3f01e850c6ba5dd5.svg","isPro":false,"fullname":"Wang","user":"Benyou","type":"user"},"name":"Benyou Wang","status":"admin_assigned","statusLastChangedAt":"2025-02-06T14:34:30.901Z","hidden":false}],"publishedAt":"2025-02-03T16:39:48.000Z","submittedOnDailyAt":"2025-02-06T00:14:36.248Z","title":"TwinMarket: A Scalable Behavioral and Social Simulation for Financial\n Markets","submittedOnDailyBy":{"_id":"643c047326f177a3e41627b6","avatarUrl":"/avatars/ade75cebd049daf080ba80a80d516240.svg","isPro":false,"fullname":"Yifei Zhang","user":"amstrongzyf","type":"user"},"summary":"The study of social emergence has long been a central focus in social\nscience. Traditional modeling approaches, such as rule-based Agent-Based Models\n(ABMs), struggle to capture the diversity and complexity of human behavior,\nparticularly the irrational factors emphasized in behavioral economics.\nRecently, large language model (LLM) agents have gained traction as simulation\ntools for modeling human behavior in social science and role-playing\napplications. Studies suggest that LLMs can account for cognitive biases,\nemotional fluctuations, and other non-rational influences, enabling more\nrealistic simulations of socio-economic dynamics. In this work, we introduce\nTwinMarket, a novel multi-agent framework that leverages LLMs to simulate\nsocio-economic systems. Specifically, we examine how individual behaviors,\nthrough interactions and feedback mechanisms, give rise to collective dynamics\nand emergent phenomena. Through experiments in a simulated stock market\nenvironment, we demonstrate how individual actions can trigger group behaviors,\nleading to emergent outcomes such as financial bubbles and recessions. Our\napproach provides valuable insights into the complex interplay between\nindividual decision-making and collective socio-economic patterns.","upvotes":38,"discussionId":"67a4215212b90b15dc5a650a","githubRepo":"https://github.com/tobyyang7/twinmarket","githubRepoAddedBy":"auto","ai_summary":"TwinMarket, a multi-agent framework using large language models, simulates socio-economic dynamics and emergent phenomena like financial bubbles and recessions in a simulated stock market.","ai_keywords":["Agent-Based Models","large language models","cognitive biases","emotional fluctuations","socio-economic dynamics","collective dynamics","emergent phenomena","simulated stock market","financial bubbles","recessions","individual decision-making"],"githubStars":45},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"643c047326f177a3e41627b6","avatarUrl":"/avatars/ade75cebd049daf080ba80a80d516240.svg","isPro":false,"fullname":"Yifei Zhang","user":"amstrongzyf","type":"user"},{"_id":"66cef20050bb4cbe31fc2247","avatarUrl":"/avatars/4c063b4caa059ae71232b72ff7c49ed5.svg","isPro":false,"fullname":"zhang","user":"stevzhang","type":"user"},{"_id":"63f622c69cbd6730302783eb","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/63f622c69cbd6730302783eb/9cb96JVKiOm_JhF-shbFw.jpeg","isPro":false,"fullname":"Yuzhe Yang","user":"TobyYang7","type":"user"},{"_id":"640ed3e9f2d7c41a1e9a9fde","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1678693486092-640ed3e9f2d7c41a1e9a9fde.jpeg","isPro":false,"fullname":"Xidong Wang","user":"Xidong","type":"user"},{"_id":"658afac6cffe7d2208657bcd","avatarUrl":"/avatars/0861bd6d394373cd9c03f207a019bc17.svg","isPro":false,"fullname":"Xuhan Huang","user":"XuhanH","type":"user"},{"_id":"64097dd1b6a334f53e2b3e4c","avatarUrl":"/avatars/18d036aab5e096054a8706bc78027126.svg","isPro":false,"fullname":"Junying Chen","user":"jymcc","type":"user"},{"_id":"64eb333e6878d90b031fa5c5","avatarUrl":"/avatars/a0d875b49d1c56be88f34854647306da.svg","isPro":false,"fullname":"Wanlong Liu","user":"lwl-uestc","type":"user"},{"_id":"65215fde728c0b6dc712dcab","avatarUrl":"/avatars/d7b8226c84b8e44876aceca6430e8326.svg","isPro":false,"fullname":"Muqi Li","user":"muqi1029","type":"user"},{"_id":"64f1a34f2c5c8b767916447e","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64f1a34f2c5c8b767916447e/uak2CsMAnxW8q4dwyAOBN.jpeg","isPro":false,"fullname":"Zhenyang Cai","user":"Eric3200","type":"user"},{"_id":"6707ca81356f027ca98fd486","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/no-auth/kAfnM35ClgM4W6zMrUFFR.png","isPro":false,"fullname":"Bairui Zhang","user":"Barryzbr12","type":"user"},{"_id":"623be9e1d1eb227788764959","avatarUrl":"/avatars/b6521b795a59754dbb40123fd4f63b8c.svg","isPro":false,"fullname":"Shunian Chen","user":"Shunian","type":"user"},{"_id":"6464481e4b34d49ac754c7db","avatarUrl":"/avatars/14612002e05ddb4b455308ef92a8d128.svg","isPro":false,"fullname":"Archer Liu","user":"tREeFrOGorigami","type":"user"}],"acceptLanguages":["*"],"dailyPaperRank":0}">
TwinMarket, a multi-agent framework using large language models, simulates socio-economic dynamics and emergent phenomena like financial bubbles and recessions in a simulated stock market.
AI-generated summary
The study of social emergence has long been a central focus in social
science. Traditional modeling approaches, such as rule-based Agent-Based Models
(ABMs), struggle to capture the diversity and complexity of human behavior,
particularly the irrational factors emphasized in behavioral economics.
Recently, large language model (LLM) agents have gained traction as simulation
tools for modeling human behavior in social science and role-playing
applications. Studies suggest that LLMs can account for cognitive biases,
emotional fluctuations, and other non-rational influences, enabling more
realistic simulations of socio-economic dynamics. In this work, we introduce
TwinMarket, a novel multi-agent framework that leverages LLMs to simulate
socio-economic systems. Specifically, we examine how individual behaviors,
through interactions and feedback mechanisms, give rise to collective dynamics
and emergent phenomena. Through experiments in a simulated stock market
environment, we demonstrate how individual actions can trigger group behaviors,
leading to emergent outcomes such as financial bubbles and recessions. Our
approach provides valuable insights into the complex interplay between
individual decision-making and collective socio-economic patterns.
🚀 We are excited to present our new research paper, "TwinMarket: A Scalable Behavioral and Social Simulation for Financial Markets". This work introduces TwinMarket, a novel multi-agent framework that leverages large language models (LLMs) to simulate socio-economic systems and emergent behavior in financial markets.
🌟 TwinMarket uses LLM-powered agents to realistically model individual investor behavior, including cognitive biases and social interactions. Our framework, built upon the Belief-Desire-Intention (BDI) model, allows agents to perceive, plan, and make decisions within a dynamic trading environment and social network. Through simulated interactions and feedback mechanisms, TwinMarket demonstrates how individual actions aggregate to form emergent phenomena. This provides valuable insights into the interplay between micro-level decision-making and macro-level socio-economic patterns. Extensive simulations demonstrate TwinMarket's ability to reproduce key stylized facts of financial markets and validate established behavioral theories.