diff --git a/README.md b/README.md
index 31ec60c4c41d5d233f81d76f95a39a1d78de0962..d4dceec6e15060a0dc9d63eec31fcf0c9ae0cf61 100644
--- a/README.md
+++ b/README.md
@@ -362,6 +362,15 @@ simulation.
 
 ### Distributed Problem Solving
 
+LLM-based Multi-Agent Systems offer several advantages: dynamic task
+decomposition with natural specialization, greater flexibility in adapting to
+system changes, and preservation of proprietary data for each participating
+entity.
+
+- **[LLM-based Multi-Agent Systems: Techniques and Business Perspectives](https://arxiv.org/abs/2411.14033)**  
+  Yingxuan Yang, Qiuying Peng, Jun Wang, Ying Wen, Weinan Zhang (2024) Published
+  on *arXiv* arXiv:2411.14033
+
 AGENTVERSE is a general multi-agent framework that simulates problem-solving
 procedures of human groups.
 
@@ -549,7 +558,6 @@ it to alternate more effectively.
   Coda-Forno, Seong Joon Oh, Matthias Bethge, Eric Schulz (2023) Published on
   arXiv
 
-
 The authors report experiments testing for altruistic behaviors among AI agents.
 Only the most sophisticated AI agent exhibits the most generous altruistic
 behavior in the dictator game, resembling human rates of sharing with other
@@ -572,8 +580,6 @@ still show limitations in adaptability.
   Shaoguang Mao, Yuzhe Cai, Yan Xia, Wenshan Wu, Xun Wang, Fengyi Wang, Qiang
   Guan, Tao Ge, Furu Wei (2025) at *COLING 2025*.
 
-
-
 This analysis shows that LLMs often stray from rational strategies, especially
 as game complexity increases. Notably, the nature of their irrationality differs
 from that of humans. The study highlights a key limitation: LLMs struggle with