Machine Spirits: Speculation and Adaptation of LLM Agents in Asset Markets

2026-04-09

AI Summary

This study investigates whether large language models (LLMs) operating in asset markets adhere to rational expectations, exhibit “animal spirits,” or manifest a distinct form of “machine spirit.” By constructing a multi-agent simulated financial market and conducting repeated-game experiments with 15 commercial and open-source LLMs under both homogeneous and heterogeneous conditions, the research reveals—for the first time—that LLM agents can spontaneously generate speculative bubbles. Heterogeneous LLM ecosystems induce endogenous instability, and individual strategy adaptation not only fails to dampen volatility but may even amplify bubble dynamics. The findings demonstrate that LLM behavior consistently deviates from rational expectations: while more advanced models can achieve profitability, they do not contribute to price stability.

Abstract

As Large Language Models (LLMs) become increasingly integrated into financial systems, understanding their behavioural properties is crucial. Do LLMs conform to the rational expectations paradigm, do they exhibit human-like"animal spirits", or do they instead manifest distinct"machine spirits"? We investigate these questions with a simulated financial market, exploring the behaviour of 15 LLMs spanning a range of sizes, capabilities, and providers. Our results show that LLMs exhibit a spectrum of economic behaviours, from stable coordination on the fundamental value to human-like speculative bubbles. These behaviours are generally inconsistent with the rational expectations hypothesis. We also consider an ecology of heterogeneous agents, a more realistic setting compared to markets with identical LLM agents. These mixed markets can produce outcomes which vary substantially across repeated simulations. Even the most advanced models fail to consistently stabilise the market, with price bubbles sometimes forming despite only a minority of agents naturally forming bubbles. Instead, advanced models in mixed markets adapt their forecasting strategies to the behaviour of other agents. This adaptation can allow them to successfully exploit less sophisticated counterparts and achieve higher profits, but can also contribute to increased market volatility. These findings suggest that the introduction of AI agents into financial markets fundamentally reshapes their ecology. In particular, heterogeneous populations of LLMs can generate endogenous instability, while individual-level adaptation may amplify, rather than mitigate, market volatility.

Problem

• Large Language Models
• Asset Markets
• Speculative Bubbles
• Market Volatility
• Agent Heterogeneity

Innovation

• machine spirits
• LLM agents
• heterogeneous agent ecology
• speculative bubbles
• adaptive forecasting