As LLMs increasingly act as autonomous agents in interactive and multi-agent settings, understanding their strategic behavior is critical for safety, coordination, and AI-driven social and economic systems. We investigate how payoff magnitude and linguistic context shape LLM strategies in repeated social dilemmas, using a payoff-scaled Prisoner's Dilemma to isolate sensitivity to incentive strength. Across models and languages, we observe consistent behavioral patterns, including incentive-sensitive conditional strategies and cross-linguistic divergence. To interpret these dynamics, we train supervised classifiers on canonical repeated-game strategies and apply them to LLM decisions, revealing systematic, model- and language-dependent behavioral intentions, with linguistic framing sometimes matching or exceeding architectural effects. Our results provide a unified framework for auditing LLMs as strategic agents and highlight cooperation biases with direct implications for AI governance and multi-agent system design.
@article{arxiv.2601.19082,
title = {More at Stake: How Payoff and Language Shape LLM Agent Strategies in Cooperation Dilemmas},
author = {Trung-Kiet Huynh and Dao-Sy Duy-Minh and Thanh-Bang Cao and Phong-Hao Le and Hong-Dan Nguyen and Nguyen Lam Phu Quy and Minh-Luan Nguyen-Vo and Hong-Phat Pham and Pham Phu Hoa and Thien-Kim Than and Chi-Nguyen Tran and Huy Tran and Gia-Thoai Tran-Le and Alessio Buscemi and Le Hong Trang and The Anh Han},
journal= {arXiv preprint arXiv:2601.19082},
year = {2026}
}