The Hunger Game Debate: On the Emergence of Over-Competition in Multi-Agent Systems
Abstract
LLM-based multi-agent systems demonstrate great potential for tackling complex problems, but how competition shapes their behavior remains underexplored. This paper investigates the over-competition in multi-agent debate, where agents under extreme pressure exhibit unreliable, harmful behaviors that undermine both collaboration and task performance. To study this phenomenon, we propose HATE, the Hunger Game Debate, a novel experimental framework that simulates debates under a zero-sum competition arena. Our experiments, conducted across a range of LLMs and tasks, reveal that competitive pressure significantly stimulates over-competition behaviors and degrades task performance, causing discussions to derail. We further explore the impact of environmental feedback by adding variants of judges, indicating that objective, task-focused feedback effectively mitigates the over-competition behaviors. We also probe the post-hoc kindness of LLMs and form a leaderboard to characterize top LLMs, providing insights for understanding and governing the emergent social dynamics of AI community.
Cite
@article{arxiv.2509.26126,
title = {The Hunger Game Debate: On the Emergence of Over-Competition in Multi-Agent Systems},
author = {Xinbei Ma and Ruotian Ma and Xingyu Chen and Zhengliang Shi and Mengru Wang and Jen-tse Huang and Qu Yang and Wenxuan Wang and Fanghua Ye and Qingxuan Jiang and Mengfei Zhou and Zhuosheng Zhang and Rui Wang and Hai Zhao and Zhaopeng Tu and Xiaolong Li and Linus},
journal= {arXiv preprint arXiv:2509.26126},
year = {2025}
}