Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.26126 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912617879044096 |
|---|---|
| author | Ma, Xinbei Ma, Ruotian Chen, Xingyu Shi, Zhengliang Wang, Mengru Huang, Jen-tse Yang, Qu Wang, Wenxuan Ye, Fanghua Jiang, Qingxuan Zhou, Mengfei Zhang, Zhuosheng Wang, Rui Zhao, Hai Tu, Zhaopeng Li, Xiaolong Linus |
| author_facet | Ma, Xinbei Ma, Ruotian Chen, Xingyu Shi, Zhengliang Wang, Mengru Huang, Jen-tse Yang, Qu Wang, Wenxuan Ye, Fanghua Jiang, Qingxuan Zhou, Mengfei Zhang, Zhuosheng Wang, Rui Zhao, Hai Tu, Zhaopeng Li, Xiaolong Linus |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_26126 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | The Hunger Game Debate: On the Emergence of Over-Competition in Multi-Agent Systems Ma, Xinbei Ma, Ruotian Chen, Xingyu Shi, Zhengliang Wang, Mengru Huang, Jen-tse Yang, Qu Wang, Wenxuan Ye, Fanghua Jiang, Qingxuan Zhou, Mengfei Zhang, Zhuosheng Wang, Rui Zhao, Hai Tu, Zhaopeng Li, Xiaolong Linus Computation and Language 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. |
| title | The Hunger Game Debate: On the Emergence of Over-Competition in Multi-Agent Systems |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2509.26126 |