LLM4AAMAS: add mao25acl

README.md

@@ -550,6 +550,19 @@ the human experimenter or an anonymous charity than with other AI agents.
   artificially intelligent agent](https://arxiv.org/abs/2301.02330)**  
   Tim Johnson, Nick Obradovich (2023) on *arXiv*.
 
+
+In this paper, the authors introduce Alympics — an "Olympics for Agents" — a
+framework that leverages large language models (LLMs) for empirical research in
+game theory. They specifically analyze how LLM agents perform in complex
+strategic scenarios, including the Water Allocation Challenge. The findings
+indicate that while LLMs are capable of accounting for long-term outcomes, they
+still show limitations in adaptability.
+
+- **[ALYMPICS: LLM Agents Meet Game Theory](https://aclanthology.org/2025.coling-main.193/)**  
+  Shaoguang Mao, Yuzhe Cai, Yan Xia, Wenshan Wu, Xun Wang, Fengyi Wang, Qiang
+  Guan, Tao Ge, Furu Wei (2025) at *COLING 2025*.
+
+
 ### Generative MAS on the shelf
 
 - [MetaGPT](https://github.com/geekan/MetaGPT) is a framework for creating