Human-AI Creative Interactions and Intelligence: Emerging Trends and Innovations

The field of human-AI creative interactions is rapidly evolving, with a growing focus on longitudinal engagements and the development of more-than-human storytelling systems. Recent research has highlighted the complex dynamics that emerge between individuals and AI narrators over time, underscoring the potential of generative AI for storytelling while also raising critical questions about user agency and ethics. Notable studies have explored the influence of different performance settings and levels of expressiveness on emotional communication and audience engagement in music performance, as well as the evaluation of generative models in music from musicological, engineering, and HCI perspectives.

A key theme emerging across these research areas is the importance of developing more natural and intimate interactions between humans and AI systems. Researchers are exploring the factors that contribute to intimacy formation, such as gradual self-disclosure, reciprocity, and naturalness, and are investigating the cognitive and metaphysical foundations of large language models (LLMs), including their ability to reason, learn, and adapt.

The development of LLMs is a crucial area of research, with a focus on improving their ability to support scientific research and facilitate more effective communication between humans and AI systems. Recent innovations include the development of interactive literature agents, frameworks for evaluating scientific knowledge update methods, and the use of LLMs to support policy researchers and systematic literature reviews.

Furthermore, researchers are working towards more flexible and scalable knowledge aggregation, with a focus on adaptive selection and fusion of multiple LLMs to build stronger models. This direction is driven by the need to overcome the limitations of traditional fine-tuning and ensemble methods, and recent innovations include the development of edge-centric multimodal frameworks and comprehensive system-level analyses of AI agents.

Overall, the field of human-AI creative interactions and intelligence is rapidly advancing, with a focus on developing more sophisticated and specialized applications of AI systems in scientific research and other areas. As researchers continue to explore the potential of generative AI, LLMs, and other AI technologies, we can expect to see significant innovations and breakthroughs in the coming years.

Sources

Advancements in Large Language Models for Scientific Research

(21 papers)

Advances in Human-AI Interaction and Intelligence

(9 papers)

Advancements in Human-AI Creative Interactions

(7 papers)

Advancements in Large Language Models

(7 papers)

Advances in Large Language Model Integration and Applications

(4 papers)

Built with on top of