The field of artificial intelligence is witnessing a significant shift towards the development of complex systems that exhibit emergent properties. Researchers are exploring the concept of emergence in Large Language Models (LLMs), where novel higher-level properties arise from the interactions of individual components. This is leading to a deeper understanding of how LLMs can be designed to solve problems more efficiently. Meanwhile, swarm intelligence is being redefined in the context of modern AI research, with LLMs being used as collaborative agents to achieve collective behavior. This has opened up new avenues for research in decentralized systems, scalability, and emergence. Notably, innovative approaches such as fully automated agentic system generation via swarm intelligence are being proposed, enabling the construction of agentic systems from scratch and joint optimization of agent functionality and collaboration. Some notable papers in this area include:

• A study that examines the emergence of capabilities in LLMs and whether they possess emergent intelligence.
• A framework for fully automated agentic system generation that achieves state-of-the-art results in real-world tasks.