Hugging Face Daily Papers · · 3 min read

Economy of Minds: Emerging Multi-Agent Intelligence with Economic Interactions

Mirrored from Hugging Face Daily Papers for archival readability. Support the source by reading on the original site.

We introduce Economy of Minds (EoM): Agents compete, trade, get wealthy, go bankrupt, and mutate, forming an evolving society where coordination and adaptation automatically emerge in a decentralized manner.</p>\n","updatedAt":"2026-06-04T09:34:00.294Z","author":{"_id":"650390d0c549d0b61839ca13","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/650390d0c549d0b61839ca13/2bFvv7csIA2xVNbVR9RRa.png","fullname":"Zhenting Qi","name":"zhenting","type":"user","isPro":true,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":8,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.7912697196006775},"editors":["zhenting"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/650390d0c549d0b61839ca13/2bFvv7csIA2xVNbVR9RRa.png"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2606.02859","authors":[{"_id":"6a202b7b15100c5272a8430d","name":"Zhenting Qi","hidden":false},{"_id":"6a202b7b15100c5272a8430e","name":"Huangyuan Su","hidden":false},{"_id":"6a202b7b15100c5272a8430f","name":"Ao Qu","hidden":false},{"_id":"6a202b7b15100c5272a84310","name":"Chenyu Wang","hidden":false},{"_id":"6a202b7b15100c5272a84311","name":"Yu Yao","hidden":false},{"_id":"6a202b7b15100c5272a84312","name":"Han Zheng","hidden":false},{"_id":"6a202b7b15100c5272a84313","name":"Kushal Chattopadhyay","hidden":false},{"_id":"6a202b7b15100c5272a84314","name":"Guowei Xu","hidden":false},{"_id":"6a202b7b15100c5272a84315","name":"Zihan Wang","hidden":false},{"_id":"6a202b7b15100c5272a84316","name":"Weirui Ye","hidden":false},{"_id":"6a202b7b15100c5272a84317","name":"Vijay Janapa Reddi","hidden":false},{"_id":"6a202b7b15100c5272a84318","name":"Ju Li","hidden":false},{"_id":"6a202b7b15100c5272a84319","name":"Paul Pu Liang","hidden":false},{"_id":"6a202b7b15100c5272a8431a","name":"Himabindu Lakkaraju","hidden":false},{"_id":"6a202b7b15100c5272a8431b","name":"Sham Kakade","hidden":false},{"_id":"6a202b7b15100c5272a8431c","name":"Yilun Du","hidden":false}],"mediaUrls":["https://cdn-uploads.huggingface.co/production/uploads/650390d0c549d0b61839ca13/FrZnUBsDqT-OvpZsPjQri.mp4"],"publishedAt":"2026-06-01T00:00:00.000Z","submittedOnDailyAt":"2026-06-04T00:00:00.000Z","title":"Economy of Minds: Emerging Multi-Agent Intelligence with Economic Interactions","submittedOnDailyBy":{"_id":"650390d0c549d0b61839ca13","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/650390d0c549d0b61839ca13/2bFvv7csIA2xVNbVR9RRa.png","isPro":true,"fullname":"Zhenting Qi","user":"zhenting","type":"user","name":"zhenting"},"summary":"How can a population of agents self-orchestrate and self-adapt into stronger collective intelligence without centralized control? Inspired by Friedrich Hayek's economic theory of decentralized coordination in markets, we study this question through an agent economy in which agents compete via auctions for the right to act, exchange payments, and accumulate wealth from environmental rewards. These simple economic signals induce decentralized credit assignment, driving planning without global orchestration or explicit communication protocols. The population evolves through economic selection: effective agents accumulate wealth and are mutated via exploitation, while ineffective ones go bankrupt and are replaced via exploration. We show that, initialized with weak agents, the economy produces emergent multi-step reasoning strategies and outperforms stronger monolithic baselines across five agentic tasks, including mathematical reasoning, financial research, scientific research, accelerator design, and distributed-system optimization. We further provide theoretical insights into how economic dynamics shape agent behaviors, linking local incentives to long-term global performance. Our results suggest a new path to multi-agent intelligence: rather than engineering coordination, we can design decentralized incentive structures under which it automatically emerges.","upvotes":5,"discussionId":"6a202b7b15100c5272a8431d","projectPage":"https://zhentingqi.github.io/internal/projects/EoM","githubRepo":"https://github.com/zhentingqi/EoM","githubRepoAddedBy":"user","ai_summary":"Decentralized agent economies with auction-based competition and wealth accumulation enable emergent collective intelligence without central coordination, outperforming monolithic approaches in complex reasoning and optimization tasks.","ai_keywords":["agent economy","decentralized coordination","auction-based competition","credit assignment","economic selection","wealth accumulation","multi-step reasoning","multi-agent intelligence","emergent behavior"],"ai_summary_model":"Qwen/Qwen2.5-Coder-32B-Instruct","githubStars":2,"organization":{"_id":"63663038361a96184dbad334","name":"Harvard","fullname":"Harvard University","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/1667641389305-6366110f575c93cedafde54e.jpeg"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"6a146bd26482105db952d83d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/ZGr6ePpjPjbgN5NZEJQTG.png","isPro":false,"fullname":"Yu Haoyu","user":"yuhaoyu53","type":"user"},{"_id":"620783f24e28382272337ba4","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/620783f24e28382272337ba4/zkUveQPNiDfYjgGhuFErj.jpeg","isPro":false,"fullname":"GuoLiangTang","user":"Tommy930","type":"user"},{"_id":"63e992cdccae1fe5c6222f84","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/63e992cdccae1fe5c6222f84/IvksSUf2DENfUwCZSmNPd.jpeg","isPro":true,"fullname":"Guowei Xu","user":"Xkev","type":"user"},{"_id":"63898e9a2a897944ea5f1453","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/63898e9a2a897944ea5f1453/EjtslshgnAn5MjKHWLIxi.png","isPro":false,"fullname":"Huangyuan Su","user":"CHL0e","type":"user"},{"_id":"68ab96fa745427e0c0ac0f8f","avatarUrl":"/avatars/3a1c4dd06cb1fb87bd759327660fb8f3.svg","isPro":false,"fullname":"Elgohary mohamed khedr","user":"elgohary47","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"organization":{"_id":"63663038361a96184dbad334","name":"Harvard","fullname":"Harvard University","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/1667641389305-6366110f575c93cedafde54e.jpeg"}}">
Papers
arxiv:2606.02859

Economy of Minds: Emerging Multi-Agent Intelligence with Economic Interactions

Published on Jun 1
· Submitted by
Zhenting Qi
on Jun 4
Authors:
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,

Abstract

Decentralized agent economies with auction-based competition and wealth accumulation enable emergent collective intelligence without central coordination, outperforming monolithic approaches in complex reasoning and optimization tasks.

How can a population of agents self-orchestrate and self-adapt into stronger collective intelligence without centralized control? Inspired by Friedrich Hayek's economic theory of decentralized coordination in markets, we study this question through an agent economy in which agents compete via auctions for the right to act, exchange payments, and accumulate wealth from environmental rewards. These simple economic signals induce decentralized credit assignment, driving planning without global orchestration or explicit communication protocols. The population evolves through economic selection: effective agents accumulate wealth and are mutated via exploitation, while ineffective ones go bankrupt and are replaced via exploration. We show that, initialized with weak agents, the economy produces emergent multi-step reasoning strategies and outperforms stronger monolithic baselines across five agentic tasks, including mathematical reasoning, financial research, scientific research, accelerator design, and distributed-system optimization. We further provide theoretical insights into how economic dynamics shape agent behaviors, linking local incentives to long-term global performance. Our results suggest a new path to multi-agent intelligence: rather than engineering coordination, we can design decentralized incentive structures under which it automatically emerges.

Community

Paper submitter about 16 hours ago

We introduce Economy of Minds (EoM): Agents compete, trade, get wealthy, go bankrupt, and mutate, forming an evolving society where coordination and adaptation automatically emerge in a decentralized manner.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.
Tap or paste here to upload images

· Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2606.02859 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2606.02859 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2606.02859 in a Space README.md to link it from this page.

Collections including this paper 1

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.

More from Hugging Face Daily Papers