arXiv：cs.AI· Zhenting Qi, Huangyuan Su, Ao Qu, Chenyu Wang, Yu Yao, Han Zheng, Kushal Chattopadhyay, Guowei Xu, Zihan Wang, Weirui Ye, Vijay Janapa Reddi, Ju Li, Paul Pu Liang, Himabindu Lakkaraju, Sham Kakade, Yilun Du·· 5 小时前
Economy of Minds：基于经济交互的多智能体智能涌现
Economy of Minds: Emerging Multi-Agent Intelligence with Economic Interactions
AI 导读
研究者提出“Economy of Minds”智能体经济框架，智能体通过拍卖竞争行动权、交换支付并从环境奖励中积累财富，无需中心化编排即可实现去中心化信用分配与全局规划。基于LLM的智能体从弱智能体起步，演化出多步推理策略，在数学推理、金融研究、科学研究、加速器设计和分布式系统优化五项任务上超越更强的单体基线。该成果被NeurIPS 2026接收。
正文
Authors:Zhenting Qi, Huangyuan Su, Ao Qu, Chenyu Wang, Yu Yao, Han Zheng, Kushal Chattopadhyay, Guowei Xu, Zihan Wang, Weirui Ye, Vijay Janapa Reddi, Ju Li, Paul Pu Liang, Himabindu Lakkaraju, Sham Kakade, Yilun Du
Abstract: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 local incentives induce decentralized credit assignment, driving global planning without explicit orchestration or 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. Using modern Large Language Model (LLM) based agents, we show that, initialized with weak agents, the agent 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. 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.
| Comments: | NeurIPS 2026 |
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA) |
| Cite as: | arXiv:2606.02859 [cs.CL] |
| (or arXiv:2606.02859v2 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2606.02859 arXiv-issued DOI via DataCite |
Submission history
From: Zhenting Qi [view email]
[v1]
Mon, 1 Jun 2026 20:21:09 UTC (559 KB)
[v2]
Tue, 13 Oct 2026 04:20:25 UTC (559 KB)
来源：arXiv：cs.AI · arxiv.org