Competitive Market Behavior of LLMs

• URL: http://arxiv.org/abs/2609.02580v1
• Date: Wed, 02 Sep 2026 13:24:42 GMT
• Title: Competitive Market Behavior of LLMs
• Abstract summary: We replace human subjects with large language models (LLMs) to test market mechanisms designed for humans.<n>We find that markets populated by LLM agents exhibit slower or no convergence towards market equilibrium.<n>We also run a lexical analysis of Chain-of-Thought traces generated by the agents.
• Score: 10.688937502565592
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) are increasingly deployed as economic agents, yet there is little evidence whether LLM agents are suited for participating in market mechanisms designed for humans, and whether these mechanisms deliver desired outcomes when faced with LLM agents. We address this question by replicating seminal economic experiments, replacing human subjects with LLM agents. We place agents in a double auction environment, which is a widely-used market mechanism. We check whether such a market is able to deliver an efficient allocation of resources, thereby testing a novel dimension of alignment of LLM agents -- their compatibility with a fundamental market mechanism. We find that markets populated by LLM agents exhibit slower or no convergence towards market equilibrium, thus providing less efficient allocations than markets populated by humans. We then analyze agents' individual trading decisions and find substantial heterogeneity both across model families and market roles. We also run a lexical analysis of Chain-of-Thought (CoT) traces generated by the agents. We find that the decision to execute a trade rather than continue incrementally adjusting prices is associated with a shift from strategic considerations toward urgency. We publicly release our testing framework, which can be used for future evaluations.

Related papers

• Strategic Exploitation in LLM Agent Markets: A Simulation Framework for E-Commerce Trust [22.530968492590848]
  We introduce TruthMarketTwin, a controlled simulation framework for studying LLM-agent behavior in e-commerce markets.<n>We find that LLM agents released into traditional markets autonomously exploit weaknesses in reputation-based governance.<n>Our results position LLM-agent simulation as a tool for studying institution-governed autonomous markets.
  arXiv  Detail & Related papers  (2026-05-11T06:36:19Z)
• Market-Bench: Benchmarking Large Language Models on Economic and Trade Competition [102.73682784993169]
  This paper introduces textbfMarket-Bench, a benchmark that evaluates the capabilities of large language models (LLMs) in economically-relevant tasks.<n>We construct a multi-agent supply chain economic model where LLMs act as retailer agents responsible for procuring and retailing merchandise.<n>Market-Bench logs complete trajectories of bids, prices, slogans, sales, and balance-sheet states, enabling automatic evaluation with economic, operational, and semantic metrics.
  arXiv  Detail & Related papers  (2026-04-07T07:23:51Z)
• Magentic Marketplace: An Open-Source Environment for Studying Agentic Markets [74.91125572848439]
  We study two-sided agentic marketplaces where Assistant agents represent consumers and Service agents represent competing businesses.<n>This environment enables us to study key market dynamics: the utility agents achieve, behavioral biases, vulnerability to manipulation, and how search mechanisms shape market outcomes.<n>Our experiments show that frontier models can approach optimal welfare-- but only under ideal search conditions. Performance degrades sharply with scale, and all models exhibit severe first-proposal bias, creating 10-30x advantages for response speed over quality.
  arXiv  Detail & Related papers  (2025-10-27T18:35:59Z)
• When Agents Trade: Live Multi-Market Trading Benchmark for LLM Agents [74.55061622246824]
  Agent Market Arena (AMA) is the first lifelong, real-time benchmark for evaluating Large Language Model (LLM)-based trading agents.<n>AMA integrates verified trading data, expert-checked news, and diverse agent architectures within a unified trading framework.<n>It evaluates agents across GPT-4o, GPT-4.1, Claude-3.5-haiku, Claude-sonnet-4, and Gemini-2.0-flash.
  arXiv  Detail & Related papers  (2025-10-13T17:54:09Z)
• Trade in Minutes! Rationality-Driven Agentic System for Quantitative Financial Trading [57.28635022507172]
  TiMi is a rationality-driven multi-agent system that architecturally decouples strategy development from minute-level deployment.<n>We propose a two-tier analytical paradigm from macro patterns to micro customization, layered programming design for trading bot implementation, and closed-loop optimization driven by mathematical reflection.
  arXiv  Detail & Related papers  (2025-10-06T13:08:55Z)
• To Trade or Not to Trade: An Agentic Approach to Estimating Market Risk Improves Trading Decisions [0.0]
  Large language models (LLMs) are increasingly deployed in agentic frameworks.<n>We develop an agentic system that uses LLMs to iteratively discover differential equations for financial time series.<n>We find that model-informed trading strategies outperform standard LLM-based agents.
  arXiv  Detail & Related papers  (2025-07-11T13:29:32Z)
• Shifting Power: Leveraging LLMs to Simulate Human Aversion in ABMs of Bilateral Financial Exchanges, A bond market study [15.379345372327375]
  TRIBE is an agent-based model augmented with a large language model (LLM) to simulate human-like decision-making in trading environments.<n>We show that incorporating human-like variability shifts power dynamics towards clients and can disproportionately affect the entire system.
  arXiv  Detail & Related papers  (2025-03-01T03:15:13Z)
• When AI Meets Finance (StockAgent): Large Language Model-based Stock Trading in Simulated Real-world Environments [55.19252983108372]
  We have developed a multi-agent AI system called StockAgent, driven by LLMs. The StockAgent allows users to evaluate the impact of different external factors on investor trading. It avoids the test set leakage issue present in existing trading simulation systems based on AI Agents.
  arXiv  Detail & Related papers  (2024-07-15T06:49:30Z)
• Deep Q-Learning Market Makers in a Multi-Agent Simulated Stock Market [58.720142291102135]
  This paper focuses precisely on the study of these markets makers strategies from an agent-based perspective. We propose the application of Reinforcement Learning (RL) for the creation of intelligent market markers in simulated stock markets.
  arXiv  Detail & Related papers  (2021-12-08T14:55:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.