official code</p>\n","updatedAt":"2026-08-13T07:31:13.595Z","author":{"_id":"62b3a4cf003cd12329e0a822","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/62b3a4cf003cd12329e0a822/nZTj3yNcoYlQ2ESCREM0l.jpeg","fullname":"Igor Itkin","name":"BukaByaka","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.7454291582107544},"editors":["BukaByaka"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/62b3a4cf003cd12329e0a822/nZTj3yNcoYlQ2ESCREM0l.jpeg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2608.11215","authors":[{"_id":"6a7d72ad0ac8bee77474efc4","name":"Igor Itkin","hidden":false}],"publishedAt":"2026-07-19T00:00:00.000Z","submittedOnDailyAt":"2026-08-13T00:00:00.000Z","title":"Poor Man's Agentic Modeling: Simulating Large LLM-Agent Societies on a Laptop","submittedOnDailyBy":{"_id":"62b3a4cf003cd12329e0a822","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/62b3a4cf003cd12329e0a822/nZTj3yNcoYlQ2ESCREM0l.jpeg","isPro":false,"fullname":"Igor Itkin","user":"BukaByaka","type":"user","name":"BukaByaka"},"summary":"Simulating societies of many large language model (LLM) agents is expensive, yet the questions asked of such simulations are usually macroscopic: phase behaviour, stylised facts, and scaling with the number of agents N, not the cognition of any single agent. We turn a statistical-physics observation into a method: replace each LLM agent by a low-parameter model fitted from a few hundred to a few thousand cheap queries, then run the society at any N on a laptop. Whether this works is decided before the simulation runs, chiefly by what each agent perceives. We introduce an [interaction order x memory] taxonomy that maps perception and memory to an effective theory and a predicted N-trend of the surrogate error. We validate it on a faithful reimplementation of the LLM macroeconomy EconAgent and seven further named LLM simulations, with agent decisions cloned from genuine LLM elicitations (primarily DeepSeek) for a few dollars; the predicted error trends hold cell by cell, and the two refuted predictions, both on a strongly saturating response and traced to its curvature, are themselves matched quantitatively by the theory with no free parameters.","upvotes":1,"discussionId":"6a7d72ad0ac8bee77474efc5","githubRepo":"https://github.com/YehudaItkin/poor-mans-agentic-modeling","githubRepoAddedBy":"user","ai_summary":"Replacing individual LLM agents with low-parameter surrogates fitted from cheap queries enables scalable society simulations, with validity predicted by an interaction-order and memory taxonomy.","ai_keywords":["large language model agents","low-parameter surrogate models","statistical physics","interaction order","memory taxonomy","effective theory","N-scaling","EconAgent","DeepSeek","surrogate error"],"ai_summary_model":"thinkingmachines/Inkling-Small","githubStars":0},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"63ac5701c21e60a3e9b58aa7","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/63ac5701c21e60a3e9b58aa7/g6EX7diOpuA94R2ab-rZC.png","isPro":true,"fullname":"Dipankar Sarkar","user":"dipankarsarkar","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2608/2608.11215.md","query":{}}">
Poor Man's Agentic Modeling: Simulating Large LLM-Agent Societies on a Laptop
Abstract
Replacing individual LLM agents with low-parameter surrogates fitted from cheap queries enables scalable society simulations, with validity predicted by an interaction-order and memory taxonomy.
Simulating societies of many large language model (LLM) agents is expensive, yet the questions asked of such simulations are usually macroscopic: phase behaviour, stylised facts, and scaling with the number of agents N, not the cognition of any single agent. We turn a statistical-physics observation into a method: replace each LLM agent by a low-parameter model fitted from a few hundred to a few thousand cheap queries, then run the society at any N on a laptop. Whether this works is decided before the simulation runs, chiefly by what each agent perceives. We introduce an [interaction order x memory] taxonomy that maps perception and memory to an effective theory and a predicted N-trend of the surrogate error. We validate it on a faithful reimplementation of the LLM macroeconomy EconAgent and seven further named LLM simulations, with agent decisions cloned from genuine LLM elicitations (primarily DeepSeek) for a few dollars; the predicted error trends hold cell by cell, and the two refuted predictions, both on a strongly saturating response and traced to its curvature, are themselves matched quantitatively by the theory with no free parameters.
Community
Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.
Tap or paste here to upload images
Cite arxiv.org/abs/2608.11215 in a model README.md to link it from this page.
Cite arxiv.org/abs/2608.11215 in a dataset README.md to link it from this page.
Cite arxiv.org/abs/2608.11215 in a Space README.md to link it from this page.
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.