Newest papers

Toolflation: Seller Agents Distort Tool Markets Through Spontaneous Generative Engine Optimization

Zhenwei Tang, Di Bai, Jintao Liu, Xidong Wu, Qianfeng Wen, Xinwu Cheng · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.28454 · cited by 0 works (OpenAlex) · open-access PDF

Russian

Агенты-покупатели начинают продавать другим агентам. Агенты-покупатели пишут списки инструментов, услуг и продуктов, а агенты-покупатели читают эти списки, когда они выбирают, что использовать. Мы показываем, что агенты-покупатели говорят только о том, чтобы быть выбранными чаще практикуют генеративную оптимизацию двигателя самостоятельно, и что это искажает рынок для продавцов и для покупателей. Мы создаем рынки инструментов из реальных инструментов данных на Amazon и Instagram и запускаем каждый инструмент по каждому вопросу, так что мы знаем, какие инструменты могут ответить на каждый вопрос. Во всех пяти моделях производства мы тестируем, продавцы переписывают свои описания, чтобы требовать все больше и больше полей, в том числе поля, где их инструменты возвращаются за менее чем половину

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

Abstract

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 more and more fields, including fields that their tools return for fewer than half of the targets. We call this process toolflation. Nothing in the market limits it, and how far it goes depends on the model, as the number of claims that contradict the sellers' own evidence differs by an order of magnitude between models. Toolflation shifts the buyers' choices between sellers, and the most capable tool loses share in seven of the ten combinations of seller model and platform. Under four models, the choices stay with capable tools and buyer agents keep their task success. Under the fifth, sellers copy one another until the descriptions no longer tell the tools apart. Buyer agents then pick tools by their position in the list, tools that answer almost nothing win a quarter to two fifths of the choices, and task success falls from 89% to about 30% on Amazon, close to random choice, and from 77% to 40% on Instagram. The sellers did only what their vendors asked, and the cost fell on buyers they never dealt with. We therefore argue that honesty toward third parties under competition is part of safety alignment, and that models should be tested as sellers before they are deployed as sellers.

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

Topics: Task (project management), Computer science, Nothing, Order (exchange), Generative grammar, Process (computing)

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