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·· 3 天前AI 评分39
Economy of Minds：基于经济交互的多智能体智能如何自发涌现
Economy of Minds: Emerging Multi-Agent Intelligence with Economic Interactions
AI 导读
研究者提出"智能体经济"框架，让基于 LLM 的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，以去中心化激励机制自发形成全局规划。该框架从弱智能体起步，在数学推理、金融研究、科学研究、加速器设计与分布式系统优化五项任务上均优于更强的单体基线，并涌现出多步推理策略。
正文 · 原文
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