LLM-Driven Multimodal Simulations: Creating Immersive Environments for Human-Computer, Human-Robot, and Social Interaction

Dear Colleagues,

Large language models (LLMs) are rapidly becoming generative engines for interactive worlds. This Special Issue examines how LLM-driven simulation generators can dynamically populate virtual, augmented, and mixed-reality spaces with intelligent agents that respond credibly through natural language, gesture, gaze, prosody, and situated behaviour. We invite original research, and rigorous case studies addressing the architectures that couple language models with perception, animation, and dialogue-management pipelines, as well as the human factors that determine whether the resulting environments succeed. Of particular interest are empirical, user-centred studies of how people perceive, calibrate trust in, and collaborate with LLM-simulated entities in real time, including how response latency, and inconsistent agent memory shape presence, workload, and sense of agency. Contributions may address embodied conversational agents and social robots, multi-agent crowd and scenario simulation, adaptive non-player characters. We welcome applications across professional training, healthcare and clinical communication, education, cultural heritage, accessibility, and collaborative work, alongside papers interrogating the ethical, safety, and governance implications of persuasive synthetic actors.

Prof. Dr. Gila Kurtz
Prof. Dr. Josep Maria Duart Montoliu
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-anonymized peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Multimodal Technologies and Interaction is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1800 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.