paper-with-me

홈 › Papers

Pay for The Second-Best Service: A Game-Theoretic Approach Against Dishonest LLM Providers

2025-11-02 · Yuhan Cao, Yu Wang, Sitong Liu, Miao Li, Yixin Tao, Tianxing He arxiv

The widespread adoption of Large Language Models (LLMs) through Application Programming Interfaces (APIs) induces a critical vulnerability: the potential for dishonest manipulation by service providers. This manipulation can manifest in various forms, such as secretly substituting a proclaimed high-performance model with a low-cost alternative, or inflating responses with meaningless tokens to increase billing. This work tackles the issue through the lens of algorithmic game theory and mechanism design. We are the first to propose a formal economic model for a realistic user-provider ecosystem, where a user can iteratively delegate $T$ queries to multiple model providers, and providers can engage in a range of strategic behaviors. As our central contribution, we prove that for a continuous strategy space and any $ε\in(0,\frac12)$, there exists an approximate incentive-compatible mechanism with an additive approximation ratio of $O(T^{1-ε}\log T)$, and a guaranteed quasi-linear second-best user utility. We also prove an impossibility result, stating that no mechanism can guarantee an expected user utility that is asymptotically better than our mechanism. Furthermore, we demonstrate the effectiveness of our mechanism in simulation experiments with real-world API settings.

📄 PDF Abstract BibTeX arXiv:2511.00847

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Interdependent Scheduling Games

2016-05-31 · Andres Abeliuk, Haris Aziz, Gerardo Berbeglia, Serge Gaspers 외

We propose a model of interdependent scheduling games in which each player controls a set of services that they schedule independently. A player is free to schedule his own services at any time; however, each of these se…

Scheduling

StratFormer: Adaptive Opponent Modeling and Exploitation in Imperfect-Information Games

2026-04-28 · Andy Caen, Mark H. M. Winands, Dennis J. N. J. Soemers arxiv

We present StratFormer, a transformer-based meta-agent that learns to simultaneously model and exploit opponents in imperfect-information games through a two-phase curriculum. The first phase trains an opponent modeling …

Automatically Reinforcing a Game AI

2016-07-27 · David L. St-Pierre, Jean-Baptiste Hoock, Jialin Liu, Fabien Teytaud 외

A recent research trend in Artificial Intelligence (AI) is the combination of several programs into one single, stronger, program; this is termed portfolio methods. We here investigate the application of such methods to …

Adaptive Learning in Continuous Games: Optimal Regret Bounds and Convergence to Nash Equilibrium

2021-04-26 · Yu-Guan Hsieh, Kimon Antonakopoulos, Panayotis Mertikopoulos

In game-theoretic learning, several agents are simultaneously following their individual interests, so the environment is non-stationary from each player's perspective. In this context, the performance of a learning algo…

All

Calibrated Stackelberg Games: Learning Optimal Commitments Against Calibrated Agents

2023-06-05 · Nika Haghtalab, Chara Podimata, Kunhe Yang arxiv

We introduce \emph{Calibrated Stackelberg Games (CSGs)}, a generalization of the standard Stackelberg Games (SGs) framework. In CSGs, a principal repeatedly interacts with an agent who (contrary to standard SGs) does not…