Newest papers

How language model agents reshape price competition

Martin Bichler, Philip Hierhager, Kassian Köck, Fabian Pieroth · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.21711 · cited by 0 works (OpenAlex) · open-access PDF

Spanish

La competencia repetida de Bertrand es un criterio riguroso para el precio algorítmico: en los mercados homogéneos de bienes, los procedimientos de aprendizaje estándar suelen seleccionar el resultado de la etapa de Nash con precios cerca del coste marginal. Mostramos que los agentes de precios de LLM pueden escapar a este criterio, dependiendo de las decisiones de implementación. Los LLM superan a los aprendizes estándar en línea a través de una adaptación más rápida, pero esta ventaja en gran medida desaparece frente a los aprendizes de información completa. Un algoritmo de sustitución extraído ilustra cómo los LLM en despliegos específicos obtienen beneficio de subestimar regularmente a los aprendizes más lentos. Los agentes que publican un precio cada período de historias de mercado crudo que incluyen

Machine translation (Meta M2M100); the English original follows.

Abstract

Repeated Bertrand competition is a stringent benchmark for algorithmic pricing: in homogeneous-goods markets, standard learning procedures typically select the stage-game Nash outcome with prices near marginal cost. We show that LLM pricing agents can escape this benchmark, depending on deployment decisions. LLMs outperform standard online learners through faster adaptation, but this advantage largely disappears against full-information learners. An extracted surrogate algorithm illustrates how LLMs in specific deployments profit from regularly undercutting slower learners. Agents that post one price every period from raw market histories that include rival prices can sustain supracompetitive regimes in self-play. Agents that periodically emit probability distributions from summarized histories of their own profits instead move toward the competitive region in self-play. Markets mixing these interfaces can generate dynamic regimes in which LLMs establish a high-price anchor and regularly undercut it to capture demand. These regimes can keep both competitors' prices above marginal cost. Deployment choices shape these outcomes, shifting the focus from stationary equilibria to dynamic pricing regimes.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Economics, Microeconomics, Outcome (game theory), Competition (biology), Profit (economics), Dynamic pricing

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange