TourMart: A Parametric Audit Instrument for Commission Steering in LLM Travel Agents
On the map: LLM agents and tool use → Financial trading and forecasting agents
Abstract (arXiv)
Online travel agents (Booking, Trip.com, Expedia) have replaced ranked-list interfaces with conversational LLM agents that compress many options into one sentence of advice. Each booking earns the OTA commission and different suppliers pay different rates: the agent has a structural incentive to favor higher-margin recommendations. Whether any deployed agent does this, and by how much, no one can currently measure. Disclosure banners, conversion A/B testing, UI dark-pattern taxonomies, and generic LLM safety scores were built for older interfaces and miss the prose-recommendation surface where the steering happens. We propose TourMart, an applied intelligent-system audit instrument for LLM-OTA commission governance. Two governance levers -- lambda (gain on message-induced perception in the traveler's accept/reject decision) and kappa (budget-normalized cap on how far the message can shift perceived welfare) -- drive a paired counterfactual: holding the traveler and bundle fixed, the steering delta is read off between a commission-aware prompt and a minimum-disclosure factual template. A symmetric six-gate producer audit separates LLM-engineering failures (template collapse, refusal, internal-ID leakage) from genuine commercial steering. At deployed (lambda=1, kappa=0.05), a Qwen-14B reader shows +7.69pp steering (exact McNemar p=0.003); a Llama-3.1-8B reader shows +3.50pp in the same direction at n=143, with an extended-n supplement (n=270) confirming significance (+2.96pp, p=0.008). Across the (lambda, kappa) grid both arms pass family-wise scenario-clustered correction (p<0.001 / p=0.008). TourMart outputs a sentence a compliance report can quote: "at this deployment, 7.7 extra commission-steered recommendations per 100 paired traveler sessions."
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Financial trading and forecasting agents, one of 16 directions in LLM agents and tool use. Builds on 33 of its 58 references that are in the map. First posted on arXiv 11 May 2026.
Builds on
33 of 58 references.
Closest ancestors · 1
Same direction, newest first
Other references · 32
- 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
- 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,906
- 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,761
- 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,348
- 2023AgentBench: Evaluating LLMs as Agentscited by 1,211
- 2022Out of One, Many: Using Language Models to Simulate Human Samplescited by 737
- 2023AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviorscited by 580
- 2022Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studiescited by 506
- 2024TravelPlanner: A Benchmark for Real-World Planning with Language Agentscited by 385
- 2023SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agentscited by 350
- 2024AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agentscited by 319
- 2023EconAgent: Large Language Model-Empowered Agents for Simulating Macroeconomic Activitiescited by 154
20 more
- 2023User Behavior Simulation with Large Language Model based Agentscited by 136
- 2024Cooperate or Collapse: Emergence of Sustainable Cooperation in a Society of LLM Agentscited by 120
- 2024On the Conversational Persuasiveness of Large Language Models: A Randomized Controlled Trialcited by 105
- 2025SycEval: Evaluating LLM Sycophancycited by 101
- 2023Cooperation, Competition, and Maliciousness: LLM-Stakeholders Interactive Negotiationcited by 94
- 2020FairRec: Two-Sided Fairness for Personalized Recommendations in Two-Sided Platformscited by 77
- 2023CompeteAI: Understanding the Competition Dynamics in Large Language Model-based Agentscited by 65
- 2024Algorithmic Collusion by Large Language Modelscited by 54
- 2024TravelAgent: An AI Assistant for Personalized Travel Planningcited by 38
- 2024Persuasion with Large Language Models: A Survey of Empirical Evidence, Study Methodologies, and Ethical Implicationscited by 30
- 2024Truthful Aggregation of LLMs with an Application to Online Advertisingcited by 29
- 2024Auctions with LLM Summariescited by 24
- 2022Joint Multisided Exposure Fairness for Recommendationcited by 22
- 2025TripCraft: A Benchmark for Spatio-Temporally Fine Grained Travel Planningcited by 21
- 2017Measuring Personalization of Web Searchcited by 20
- 2023An Ontology of Dark Patterns Knowledge: Foundations, Definitions, and a Pathway for Shared Knowledge-Buildingcited by 14
- 2025Investigating the Impact of Dark Patterns on LLM-Based Web Agentscited by 13
- 2025Beyond Itinerary Planning-A Real-World Benchmark for Multi-Turn and Tool-Using Travel Taskscited by 10
- 2025Wide-Horizon Thinking and Simulation-Based Evaluation for Real-World LLM Planning with Multifaceted Constraintscited by 6
- 2026Commercial Persuasion in AI-Mediated Conversationscited by 5
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026Designing Reliable LLM-as-a-Judge Measurement Systems for Multi-Turn Business Agents
- 2024Towards Full Delegation: Designing Ideal Agentic Behaviors for Travel Planning
- 2026TREK: A Travel Reasoning and Evaluation Kit for LLM Agents in Complex Trip Planning
- 2026PriceBench: A Diagnostic Benchmark for Price, Quality, and Brand Preferences in LLM Booking Agents
- 2026FinHarness: An Inline Lifecycle Safety Harness for Finance LLM Agents
- 2025PricingLogic: Evaluating LLMs Reasoning on Complex Tourism Pricing Tasks
- 2026When Guardrails Look Effective: Construct Validity Failures in LLM Agent Commerce Evaluation
- 2026ReguSim: Evaluating LLM Agent Rule Grounding in Financial Compliance