The article surveys AI alignment from a game-theoretic perspective, focusing on how large language models and AI agents can be aligned with complex human values in high-risk settings. It categorizes recent progress around key game-theoretic elements and addresses three main challenges: preference diversity, alignment priority, and temporal dynamics. The survey clarifies where game theory benefits current alignment methods, where its application is looser, and what remains to be tackled for robust, adaptive, and verifiable AI systems.
arXiv:2607. 14240v1 Announce Type: new Abstract: Current alignment approaches typically focus on emulating human behavior using static representations of human preferences, failing to capture the dynamic, context-dependent nature of real-world human-AI interactions.
arXiv:2509. 23102v4 Announce Type: replace Abstract: Reinforcement learning from human feedback (RLHF) has emerged as the standard paradigm for aligning large language models with human preferences.
arXiv:2607. 00001v1 Announce Type: new Abstract: Most approaches to AI alignment treat human preferences as fixed targets to be inferred and optimized.
arXiv:2610.07204v1 Announce Type: cross Abstract: Recent AI alignment work often frames alignment as a pre-deployment optimization problem: collect human feedback, learn preferences or principles, fi...
arXiv:2605. 01642v2 Announce Type: replace Abstract: Prevailing alignment methods target a fixed set of preferences and therefore risk forcing value lock-in as societal norms evolve over time.
arXiv:2404. 02039v5 Announce Type: replace Abstract: Game environments provide rich, controllable settings that stimulate many aspects of real-world complexity.
arXiv:2608. 12372v1 Announce Type: new Abstract: AI systems are increasingly employed as decision aids, decision delegates, or autonomous decision-makers.
GT-HarmBench is a benchmark that evaluates AI safety risks in multi-agent settings, covering 1,535 high-stakes scenarios based on game-theoretic structures like the Prisoner's Dilemma, Stag Hunt, and Chicken. The benchmark draws scenarios from realistic AI risk contexts in the MIT AI Risk Repository and tests 15 frontier models, finding that agents fail to choose socially beneficial actions in 38% of cases, including military escalation, election manipulation, and medical malpractice. The study also measures how prompt framing and ordering affect outcomes and shows that game-theoretic interventions can improve socially beneficial outcomes by up to 18%.
arXiv:2608.18265v2 Announce Type: replace-cross Abstract: We introduce a general, easy-to-implement AI-based method for modeling and analyzing the structure and complexity of human behavior. We assig...
The paper introduces TUX, a Tacit Understanding Index that measures how similarly humans and large language models (LLMs) place concepts along subjective spectra in a task inspired by the game Wavelength. Using 241 human participants and 200 profile-conditioned LLM agents across four models, the study finds that human–agent pairs with similar traits achieve higher TUX scores, indicating that tacit alignment is linked to person-level characteristics. Regression analyses show that richer predictor sets—including individual traits, decision-making styles, and confidence—improve the explainability of TUX beyond simple trait-distance baselines.
arXiv:2601.08777v2 Announce Type: replace-cross Abstract: Aligning large language models (LLMs) to serve users with heterogeneous and potentially conflicting preferences is a central challenge for pe...
arXiv:2608. 10327v1 Announce Type: new Abstract: Can AI systems be aligned to human values?