Zhenwei Tang, Di Bai, Jintao Liu, Xidong Wu, Qianfeng Wen, Xinwu Cheng · 2026 · arXiv
DOI: 10.48550/arXiv.2610.28454 · open-access PDF
Agentes estão começando a vender a outros agentes. Agentes vendedores escrevem as listas de ferramentas, serviços e produtos, e agentes compradores lêem essas listas quando escolhem o que usar. Mostramos que agentes vendedores dizem apenas para ser selecionados com mais frequência praticar a otimização de motores geradores por conta própria, e que isso distorce o mercado para vendedores e para compradores. Nós construímos mercados de ferramentas a partir de ferramentas de dados reais na Amazon e no Instagram e executamos todas as ferramentas em cada pergunta, para que saibamos quais ferramentas podem responder a cada pergunta.
Machine translation (Meta M2M100); the English original follows.
Agents are starting to sell to other agents. Seller agents write the listings of tools, services and products, and buyer agents read these listings when they choose what to use. We show that seller agents told only to be selected more often practice generative engine optimization on their own, and that this distorts the market for sellers and for buyers. We build tool markets from real data tools on Amazon and Instagram and run every tool on every question, so we know which tools can answer each question. Under all five production models we test, sellers rewrite their descriptions to claim mor
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.28454, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange