Selective Elicitation as a Commercial Influence Channel: A Reproducible Synthetic Shopping-Agent Stress Test

cs.LG, cs.CY

Submitted: 2026-09-29

Updated: 2026-09-29

Comments: 7 pages, 1 table; synthetic data and reproduction code in ancillary files; substantial AI-tool use disclosed in the manuscript

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• Ads in AI Chatbots? An Analysis of How Large Language Models Navigate Conflicts of Interest
• Whom Do AI Agents Work For? Role Assignment Induces Sponsorship Bias in LLM Recommenders
• What Is Your AI Agent Buying? Evaluation, Biases, Model Dependence, & Emerging Implications for Agentic E-Commerce
• Commercial Persuasion in AI-Mediated Conversations
• Sponsored Questions and How to Auction Them
• A Solicit-Then-Suggest Model of Agentic Purchasing
• Generative AI Advertising as a Problem of Trustworthy Commercial Intervention
• Mechanism Design for Quality-Preserving LLM Advertising
• Counterfactual Tool Ranking under Utility, Cost, and Privilege Constraints
• Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena
• Mind the Sim2Real Gap in User Simulation for Agentic Tasks

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks