Project Riley: Multimodal Multi-Agent LLM Collaboration with Emotional Reasoning and Voting

This paper presents Project Riley, a novel multimodal and multi-model conversational AI architecture oriented towards the simulation of reasoning influenced by emotional states. Drawing inspiration from Pixar's Inside Out, the system comprises five distinct emotional agents - Joy, Sadness, Fear, Anger, and Disgust - that engage in structured multi-round dialogues to generate, criticise, and iteratively refine responses. A final reasoning mechanism synthesises the contributions of these agents into a coherent output that either reflects the dominant emotion or integrates multiple perspectives. The architecture incorporates both textual and visual large language models (LLMs), alongside advanced reasoning and self-refinement processes. A functional prototype was deployed locally in an offline environment, optimised for emotional expressiveness and computational efficiency. From this initial prototype, another one emerged, called Armando, which was developed for use in emergency contexts, delivering emotionally calibrated and factually accurate information through the integration of Retrieval-Augmented Generation (RAG) and cumulative context tracking. The Project Riley prototype was evaluated through user testing, in which participants interacted with the chatbot and completed a structured questionnaire assessing three dimensions: Emotional Appropriateness, Clarity and Utility, and Naturalness and Human-likeness. The results indicate strong performance in structured scenarios, particularly with respect to emotional alignment and communicative clarity.

Robustness Evaluation of Regression Tasks with Skewed Domain Preferences

In natural phenomena, data distributions often deviate from normality. One can think of cataclysms as a self-explanatory example: events that occur almost never, and at the same time are many standard deviations away from the common outcome. In many scientific contexts it is exactly these tail events that researchers are most interested in anticipating, so that adequate measures can be taken to prevent or attenuate a major impact on society. Despite such efforts, we have yet to provide definite answers to crucial issues in evaluating predictive solutions in domains such as weather, pollution, health. In this paper, we deal with two encapsulated problems simultaneously. First, assessing the performance of regression models when non-uniform preferences apply - not all values are equally relevant concerning the accuracy of their prediction, and there's a particular interest in the most extreme values. Second, assessing the robustness of models when dealing with uncertainty regarding the actual underlying distribution of values relevant for such problems. We show how different levels of relevance associated with target values may impact experimental conclusions, and demonstrate the practical utility of the proposed methods.