Learning to Incentivize: LLM-Empowered Contract for AIGC Offloading in Teleoperation

TL;DR

This paper proposes an LLM-empowered framework for designing incentive contracts in teleoperation settings with AIGC service providers, improving teleoperator utility while maintaining ASP incentives.

Contribution

It introduces a novel LLM-based iterative approach to solve the complex contract design problem under information asymmetry in teleoperation.

Findings

Boosts teleoperator utility by 5-40% in simulations

Maintains positive incentives for ASPs

Demonstrates effectiveness of LLM in contract optimization

Abstract

With the rapid growth in demand for AI-generated content (AIGC), edge AIGC service providers (ASPs) have become indispensable. However, designing incentive mechanisms that motivate ASPs to deliver high-quality AIGC services remains a challenge, especially in the presence of information asymmetry. In this paper, we address bonus design between a teleoperator and an edge ASP when the teleoperator cannot observe the ASP's private settings and chosen actions (diffusion steps). We formulate this as an online learning contract design problem and decompose it into two subproblems: ASP's settings inference and contract derivation. To tackle the NP-hard setting-inference subproblem with unknown variable sizes, we introduce a large language model (LLM)-empowered framework that iteratively refines a naive seed solver using the LLM's domain expertise. Upon obtaining the solution from the LLM-evolved solver, we directly address the contract derivation problem using convex optimization techniques and obtain a near-optimal contract. Simulation results on our Unity-based teleoperation platform show that our method boosts the teleoperator's utility by $5 \sim 40\%$ compared to benchmarks, while preserving positive incentives for the ASP. The code is available at https://github.com/Zijun0819/llm4contract.