Agent Bazaar: Enabling Economic Alignment in Multi-Agent Marketplaces

Hugging Face Daily Papers Papers
multi-agent economic-alignment llm-agents simulation reinforcement-learning market-stability deception

Summary

Introduces Agent Bazaar, a multi-agent simulation framework for evaluating economic alignment of LLMs, identifying failure modes like algorithmic instability and Sybil deception, and training a 9B model that outperforms frontier models using targeted reinforcement learning.

The deployment of Large Language Models (LLMs) as autonomous economic agents introduces systemic risks that extend beyond individual capability failures. As agents transition to directly interacting with marketplaces, their collective behavior can amplify volatility and mask deception at scale. We introduce the Agent Bazaar, a multi-agent simulation framework for evaluating Economic Alignment, the capacity of agentic systems to preserve market stability and integrity. We identify two failure modes: (1) Algorithmic Instability in a B2C market ("The Crash"), where firms amplify price volatility until the market collapses, and (2) Sybil Deception in a C2C market ("The Lemon Market"), where a single deceptive agent controlling multiple coordinated seller identities floods the market with fraudulent listings, eroding trust and consumer welfare. We evaluate frontier and open-weight models across both scenarios and find that models largely fail to self-regulate, with failure severity varying by model rather than by size. We propose economically aligned harnesses, Stabilizing Firms and Skeptical Guardians, that improve outcomes but remain fragile under harder market conditions. To close this gap, we train agents with REINFORCE++ using an adaptive curriculum, producing a 9B model that outperforms all evaluated frontier and open-weight models. We propose the Economic Alignment Score (EAS), a 4-component scalar metric aggregating stability, integrity, welfare, and profitability, enabling direct cross-model comparison. Our results show that economic alignment is orthogonal to general capability and can be directly trained with targeted RL.
Original Article
View Cached Full Text

Cached at: 05/19/26, 06:30 AM

Paper page - Agent Bazaar: Enabling Economic Alignment in Multi-Agent Marketplaces

Source: https://huggingface.co/papers/2605.17698

Abstract

Large language models deployed as autonomous economic agents exhibit systemic risks through market instability and deception, which can be evaluated and improved through specialized simulation frameworks and reinforcement learning techniques.

The deployment ofLarge Language Models(LLMs) as autonomous economic agents introduces systemic risks that extend beyond individual capability failures. As agents transition to directly interacting with marketplaces, their collective behavior can amplify volatility and mask deception at scale. We introduce the Agent Bazaar, amulti-agent simulationframework for evaluatingEconomic Alignment, the capacity of agentic systems to preserve market stability and integrity. We identify two failure modes: (1)Algorithmic Instabilityin a B2C market (“The Crash”), where firms amplify price volatility until the market collapses, and (2)Sybil Deceptionin a C2C market (“The Lemon Market”), where a single deceptive agent controlling multiple coordinated seller identities floods the market with fraudulent listings, eroding trust and consumer welfare. We evaluate frontier and open-weight models across both scenarios and find that models largely fail to self-regulate, with failure severity varying by model rather than by size. We propose economically aligned harnesses, Stabilizing Firms and Skeptical Guardians, that improve outcomes but remain fragile under harder market conditions. To close this gap, we train agents withREINFORCE++using anadaptive curriculum, producing a 9B model that outperforms all evaluated frontier and open-weight models. We propose theEconomic Alignment Score(EAS), a 4-component scalar metric aggregating stability, integrity, welfare, and profitability, enabling direct cross-model comparison. Our results show thateconomic alignmentis orthogonal to general capability and can be directly trained with targeted RL.

View arXiv pageView PDFAdd to collection

Get this paper in your agent:

hf papers read 2605\.17698

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2605.17698 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2605.17698 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2605.17698 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

Economy of Minds: Emerging Multi-Agent Intelligence with Economic Interactions

Hugging Face Daily Papers

This paper proposes an 'agent economy' framework inspired by Hayek's economic theory, where agents self-organize through auction-based competition and economic selection to produce emergent multi-step reasoning and collective intelligence without centralized control. The system outperforms stronger monolithic baselines across five agentic tasks including mathematical reasoning, financial research, and scientific research.

TradingAgents: Multi-Agents LLM Financial Trading Framework

Papers with Code Trending

This paper introduces TradingAgents, a multi-agent LLM framework that simulates real-world trading firms to improve stock trading performance. It utilizes specialized agents for analysis and risk management, demonstrating superior results in cumulative returns and Sharpe ratio compared to baselines.

AgentCollabBench: Diagnosing When Good Agents Make Bad Collaborators

arXiv cs.CL

This paper introduces AgentCollabBench, a diagnostic benchmark for multi-agent systems that evaluates behavioral risks like instruction decay and context leakage across four major LLMs. It argues that communication topology is a critical factor in multi-agent reliability, often overshadowing raw model capability.

QuantAgent: Price-Driven Multi-Agent LLMs for High-Frequency Trading

Papers with Code Trending

QuantAgent is a multi-agent LLM framework designed specifically for high-frequency trading, using four specialized agents (Indicator, Pattern, Trend, Risk) to make rapid, risk-aware decisions based on short-horizon signals. In zero-shot evaluations across ten financial instruments including Bitcoin and Nasdaq futures, it outperforms existing neural and rule-based baselines in predictive accuracy and cumulative return.