Magentic Marketplace: An Open-Source Environment for Studying Agentic Markets

• URL: http://arxiv.org/abs/2510.25779v1
• Date: Mon, 27 Oct 2025 18:35:59 GMT
• Title: Magentic Marketplace: An Open-Source Environment for Studying Agentic Markets
• Authors: Gagan Bansal, Wenyue Hua, Zezhou Huang, Adam Fourney, Amanda Swearngin, Will Epperson, Tyler Payne, Jake M. Hofman, Brendan Lucier, Chinmay Singh, Markus Mobius, Akshay Nambi, Archana Yadav, Kevin Gao, David M. Rothschild, Aleksandrs Slivkins, Daniel G. Goldstein, Hussein Mozannar, Nicole Immorlica, Maya Murad, Matthew Vogel, Subbarao Kambhampati, Eric Horvitz, Saleema Amershi,
• Abstract summary: 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.
• Score: 74.91125572848439
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: As LLM agents advance, they are increasingly mediating economic decisions, ranging from product discovery to transactions, on behalf of users. Such applications promise benefits but also raise many questions about agent accountability and value for users. Addressing these questions requires understanding how agents behave in realistic market conditions. However, previous research has largely evaluated agents in constrained settings, such as single-task marketplaces (e.g., negotiation) or structured two-agent interactions. Real-world markets are fundamentally different: they require agents to handle diverse economic activities and coordinate within large, dynamic ecosystems where multiple agents with opaque behaviors may engage in open-ended dialogues. To bridge this gap, we investigate two-sided agentic marketplaces where Assistant agents represent consumers and Service agents represent competing businesses. To study these interactions safely, we develop Magentic-Marketplace-- a simulated environment where Assistants and Services can operate. 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. 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. These findings reveal how behaviors emerge across market conditions, informing the design of fair and efficient agentic marketplaces.

Related papers

• Evaluating Generalization Capabilities of LLM-Based Agents in Mixed-Motive Scenarios Using Concordia [100.74015791021044]
  Large Language Model (LLM) agents have demonstrated impressive capabilities for social interaction.<n>Existing evaluation methods fail to measure how well these capabilities generalize to novel social situations.<n>We present empirical results from the NeurIPS 2024 Concordia Contest, where agents were evaluated on their ability to achieve mutual gains.
  arXiv  Detail & Related papers  (2025-12-03T00:11:05Z)
• Multi-Agent Reinforcement Learning for Market Making: Competition without Collusion [6.598173855286935]
  We propose a hierarchical multi-agent reinforcement learning framework to study algorithmic collusion in market making.<n>The framework includes a self-interested market maker (AgentA), which is trained in an uncertain environment shaped by an adversary.<n>We show that adaptive incentive control supports more sustainable strategic co-existence in heterogeneous agent environments.
  arXiv  Detail & Related papers  (2025-10-29T20:07:47Z)
• Towards General Agentic Intelligence via Environment Scaling [78.66355092082253]
  Advanced agentic intelligence is a prerequisite for deploying Large Language Models in real-world applications.<n>We design a scalable framework that automatically constructs heterogeneous environments that are fully simulated.<n>Experiments on agentic benchmarks, tau-bench, tau2-Bench, and ACEBench, demonstrate that our trained model, AgentScaler, significantly enhances the function-calling capability of models.
  arXiv  Detail & Related papers  (2025-09-16T17:57:20Z)
• Evaluating LLM Agent Collusion in Double Auctions [1.3194391758295114]
  We study the behavior of large language models (LLMs) acting as sellers in simulated double auction markets.<n>We find that direct seller communication increases collusive tendencies, the propensity to collude varies across models, and environmental pressures, such as oversight and urgency from authority figures, influence collusive behavior.
  arXiv  Detail & Related papers  (2025-07-02T07:06:49Z)
• The Real Barrier to LLM Agent Usability is Agentic ROI [110.31127571114635]
  Large Language Model (LLM) agents represent a promising shift in human-AI interaction.<n>We highlight a critical usability gap in high-demand, mass-market applications.
  arXiv  Detail & Related papers  (2025-05-23T11:40:58Z)
• The Agentic Economy [46.77230659526348]
  We argue that the more profound economic impact lies in reducing communication frictions between consumers and businesses.<n>This shift could reorganize markets, redistribute power, and catalyze the creation of new products and services.
  arXiv  Detail & Related papers  (2025-05-21T17:51:36Z)
• 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)
• Stochastic Market Games [10.979093424231532]
  We propose to utilize market forces to provide incentives for agents to become cooperative. As demonstrated in an iterated version of the Prisoner's Dilemma, the proposed market formulation can change the dynamics of the game. We empirically find that the presence of markets can improve both the overall result and agent individual returns via their trading activities.
  arXiv  Detail & Related papers  (2022-07-15T10:37:16Z)

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.