Searcharxiv⌕ Search

arXiv · 2609.31468

PriceBench: A Diagnostic Benchmark for Price, Quality, and Brand Preferences in LLM Booking Agents

Abstract

LLMs increasingly act as purchasing agents, which makes the LLM, not the user, the one choosing among the options that satisfy a request; its preferences quietly fix what gets bought and what it costs. Hotel booking is a clean instance: a high-volume choice settled on a few comparable attributes, where the pick reveals those preferences. We introduce PriceBench, a diagnostic benchmark that recovers an LLM's price, quality, and brand preferences from its booking choices with a logit choice model, applied to 28 LLMs from 8 providers on 3,600 hotel tasks from 179 real New York City properties. We find that capability is associated with how consistently an LLM chooses, not with what it chooses: more capable LLMs hold stronger, more consistent preferences, while weaker ones either lock onto one position, exploitable by whoever controls listing order, or choose almost indifferently. What those preferences favor varies sharply across providers and even within one family: price sensitivity spans more than an order of magnitude, and the price/quality trade-off moves mean booked nightly price from \$247 to \$393 on identical tasks. What an agent buys must therefore be measured per LLM, not inferred, and we release the tasks, code, and all 28 response sets.

Explore related subjects

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Pavel Kireyev. 2026-09-25. PriceBench: A Diagnostic Benchmark for Price, Quality, and Brand Preferences in LLM Booking Agents. https://searcharxiv.com/abs/2609.31468

Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.

KEEP EXPLORING

Related papers

Just After Minimum Wage Hikes: Short-Run Labor-Demand Response and Reallocation

How labor markets adjust immediately after minimum wage hikes remains an open, policy-relevant question. This paper studies short-run minimum-wage effects in Japan's spot labor market using Timee data and a wage-bin difference-in-differences design. We find a normalized net employment-share change of $-0.010$, with similar estimates for vacancies and total working hours. Weekly and daily estimates show that these effects emerge immediately after implementation and then stabilize. Effects are more negative where the minimum-wage bite is higher and in restaurant work. Net share effects are negative for midnight shifts and postings offering transportation reimbursement. Gender-targeted and beginner-targeted postings show no significant net change. Decomposing vacancies by employers' posting histories, we find that incumbent employers cut postings below the new floor while employers that did not post before the revision post just above it. Cross-employer reallocation, a multi-year process in standard labor markets, thus begins immediately in spot gig work.

econ.GN↗

AI Adoption in S&P 500 Firms

The adoption of artificial intelligence (AI) by large enterprises is an important potential source of aggregate productivity improvement and labor market impact. We study AI adoption of S&P 500 firms over the period 2016 to 2025, estimating adoption at the enterprise level. While generative AI tools are useful for personal and professional applications, our focus is on the deep integration of AI in the business processes of large enterprises which are bellwethers for firm adoption more broadly. We develop a novel measure to assess deep AI adoption (and distinguish it from AI hype) that is based on SEC 10-K filings, where laws and regulations ``prohibit companies from making materially false or misleading statements." In 2025, 11% of S&P 500 enterprises had AI deeply integrated into their business processes, and a further 10% were using AI in the production of goods and delivery of services. AI adoption has more than quadrupled from 5% in 2022 with slowly accelerating adoption among non-technology firms but very aggressive adoption in the technology sector which accounts for two-thirds of deeply integrated enterprise adoption. Firm profitability shows a "J-curve" as firms move from no adoption to deep adoption, but we observe no differences in capex or productivity. Among technology firms, but not others, AI adoption is higher for firms with more employees and higher values of Tobin's q.

econ.GN↗

Clicks, Carbon, and Risk: Climate Attention, Persistent Financial Risk, and Real-Sector Activity

Do shifts in public climate concern alter persistent financial risk and subsequently matter for real activity? We combine daily U.S. sectoral equity returns with a monthly Climate Concern Index (CCI) constructed from internet search intensity and decomposed into adverse and transition-oriented components. GARCH-MIDAS estimates reveal substantial heterogeneity: adverse climate concern raises persistent volatility in carbon-intensive Energy activities, while transition-oriented attention tends to reduce persistent volatility in regulated Utilities, with important differences across sub-sectors. We then construct a persistent-risk differential between Energy and Utilities and examine its predictive content for sectoral real activity using local projections. Innovations associated with adverse climate concern precede declines in Oil and Gas industrial production and employment over the following quarters, while comparable Utilities responses are limited. The production result is preserved when the financial predictor is reconstructed using the more closely matched Oil, Gas, Coal equity sub-sector and remains economically similar across several robustness checks. Overall, the findings establish a link between climate concern, persistent sectoral financial risk, and subsequent real-sector activity.

econ.GN↗