Incentive-Aware Multi-Fidelity Optimization for Generative Advertising in Large Language Models

ACL ARR 2026 January Submission6649 Authors

Keywords: Generative Advertising, Multi-fidelity Optimization, Mechanism Design, VCG Mechanism

Abstract: Generative advertising in Large Language Model (LLM) chatbots requires optimizing sponsorship configurations under two strict constraints: the strategic behavior of advertisers and the high cost of per-query best-of-N stochastic generations. To address this, we propose the Incentive-Aware Multi-Fidelity Mechanism (IAMFM), a unified framework coupling Vickrey-Clarke-Groves (VCG) incentives with Multi-Fidelity Optimization to maximize expected social welfare offline. We compare two algorithmic instantiations--elimination-based and model-based--revealing their budget-dependent performance trade-offs. Crucially, to make VCG computationally feasible, we introduce Active Counterfactual Optimization, a "warm-start" that reuses optimization data for efficient payment calculation. We provide formal guarantees for approximate strategy-proofness and individual rationality, establishing a general approach for incentive-aligned, budget-constrained generative processes. Experiments demonstrate that IAMFM outperforms single-fidelity baselines across diverse budgets.

Paper Type: Long

Research Area: AI/LLM Agents

Research Area Keywords: multi-agent systems, agent coordination and negotiation, optimization methods, financial/business NLP, LLM agents, generative models

Contribution Types: Approaches low compute settings-efficiency, Theory

Languages Studied: English

Submission Number: 6649