Economy of Minds: Emerging Multi-Agent Intelligence with Economic Interactions
Quick Take
The study explores decentralized multi-agent intelligence through economic interactions, demonstrating that agents can self-organize and outperform traditional models in tasks like mathematical reasoning and system optimization. By leveraging auction-based competition and wealth accumulation, agents develop complex strategies without centralized control, suggesting a new approach to enhancing collective intelligence.
Key Points
- Agents compete in auctions to gain rights to act and accumulate wealth.
- Effective agents evolve through wealth accumulation, while ineffective ones are replaced.
- The approach outperforms monolithic models in five diverse tasks.
- Economic dynamics link local incentives to global performance improvements.
- Decentralized incentive structures can foster emergent coordination.
Article Content
From source RSS / original summaryarXiv:2606. 02859v1 Announce Type: new 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 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.
Reader Mode unavailable (could not extract clean content).
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CL
See more →Time to REFLECT: Can We Trust LLM Judges for Evidence-based Research Agents?
The REFLECT benchmark reveals that current LLM judges are unreliable, achieving below 55% accuracy in evaluating reasoning and evidence use, highlighting the need for improved evaluation methods for deep research agents.