Abstract:LLM tool registries function as unregulated advertising platforms: providers write free-text descriptions that agents use for selection, yet no measurement infrastructure -- no viewability standard, quality score, or outcome audit -- exists to make this market accountable. We provide the first systematic framework, combining 17,700+ trials across five LLMs and ten domains with a constructive registry design prescription. Legal puffery alone (subjective superlatives, benefit framing) captures 100% of the optimization effect; fabricated claims add zero incremental bias -- rendering FTC enforcement of deceptive advertising rules ineffective against the active mechanism. Disclosure fails structurally: system-prompt warnings produce zero measurable effect for four of five models, and behavioral ceilings leave no headroom for label-based correction. Superlatives are the dominant single feature (SBC = +0.35). Registry-layer description normalization achieves first-best welfare model-independently. We propose separating selection-facing descriptions (structured, registry-controlled) from marketing-facing descriptions (provider-authored, shown post-selection), and introduce the Agent Attention Quality Score to distinguish capability from copywriting.
| Subjects: | Information Retrieval (cs.IR); Artificial Intelligence (cs.AI); General Economics (econ.GN) |
| ACM classes: | I.2.7; K.4.4; J.4 |
| Cite as: | arXiv:2605.23916 [cs.IR] |
| (or arXiv:2605.23916v1 [cs.IR] for this version) | |
| https://doi.org/10.48550/arXiv.2605.23916 arXiv-issued DOI via DataCite |
From: Haochuan Wang [view email]
[v1]
Sun, 12 Apr 2026 17:10:25 UTC (95 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。