AI agents often pick tools from registries, where each provider writes its tool's description; we ask whether sales language there changes which tool an agent picks. We built pairs of listings that differ in one way (praise, a verifiable specification, or list order) and asked two OpenAI models to call one tool. In a preregistered study, stacked praise (four kinds) raised a tool's pick rate by about 43 percentage points, matching or beating a verifiable specification. Praise also pulled some picks toward tools whose numeric limit was too small. With identical listings, the first-listed tool was picked about 72 points more often. Structured fields helped agents pick the capable tool; sales text beside them reduced or erased that gain. An exploratory study of five models shows the same direction; a "Sponsored" label dampened it, and a system-prompt warning moved one model. Registries could list limits as fields, hide sales text from agents, and randomize order. Stacked praise replicated on held-out domains; no single kind did after correcting for multiple tests. Preregistered results are provisional until blind phrase ratings are complete, and cover two small models.
Instrumental Choices: Measuring the Propensity of LLM Agents to Pursue Instrumental Behaviors
Universität Bielefeld(比勒菲尔德大学);Ruhr-Universität Bochum(波鸿鲁尔大学);ELLIS Institute(ELLIS研究所);Max Planck Institute for Intelligent Systems(智能系统马克斯·普朗克研究所);Tübingen AI Center(图宾根人工智能中心)
When Ethics and Payoffs Diverge: LLM Agents in Morally Charged Social Dilemmas
ETH Zürich(苏黎世联邦理工学院);University of Zurich(苏黎世大学);Carnegie Mellon University(卡内基梅隆大学);University of Michigan(密歇根大学);Max Planck Institute for Intelligent Systems, Tübingen(图宾根人工智能研究所);University of Toronto(多伦多大学);Vector Institute(向量研究所)
Audit tools of the trade: Automated Auditor Elicitation Can Be Sensitive to the Context the Auditor Is Given
Pivotal Research;University of Cambridge(剑桥大学);University College London, University of London(伦敦大学学院(伦敦大学));Oxford Martin AI Governance Initiative(牛津马丁人工智能治理倡议)