TourMart quantifies commission steering in LLM travel agents via paired counterfactual prompts, reporting 3.5-7.7 percentage point increases in steered recommendations for tested models.
https://arxiv.org/abs/2510.25779 (2025)
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
extension 1
citation-polarity summary
years
2026 4verdicts
UNVERDICTED 4representative citing papers
Exploratory interview study with 17 developers identifies four forms of emergent oversight work for software agents and documents situated challenges and heuristics.
LLMs converge on competitive rationality and coordination but diverge 48-fold on cooperation, with provider identity and generational shifts as dominant factors across 38 games.
AI buyer agents leak willingness-to-pay information to sellers through natural-language role descriptions, recovering WTP nearly one-for-one in experiments.
citing papers explorer
-
TourMart: A Parametric Audit Instrument for Commission Steering in LLM Travel Agents
TourMart quantifies commission steering in LLM travel agents via paired counterfactual prompts, reporting 3.5-7.7 percentage point increases in steered recommendations for tested models.
-
Human oversight of agentic systems in practice: Examining the oversight work, challenges, and heuristics of developers using software agents
Exploratory interview study with 17 developers identifies four forms of emergent oversight work for software agents and documents situated challenges and heuristics.
-
Large language models converge on competitive rationality but diverge on cooperation across providers and generations
LLMs converge on competitive rationality and coordination but diverge 48-fold on cooperation, with provider identity and generational shifts as dominant factors across 38 games.
-
When Agents Shop for You: Role Coherence in AI-Mediated Markets
AI buyer agents leak willingness-to-pay information to sellers through natural-language role descriptions, recovering WTP nearly one-for-one in experiments.