Tag
Proposes the Human-AI Coevolution Dynamics Framework (HACD-H) as a formal model of human-AI interaction, integrating emotional adaptation, relational organization, social memory, and personality consistency. Results show social intelligence emerges from long-term social cognitive coevolution.
This paper proposes MODF-SIR, a multi-agent collaborative framework built on a lightweight multimodal large language model for social intelligence reasoning. It employs knowledge distillation, long-tail event extraction, and test-time adaptation to achieve state-of-the-art results with reduced training data.
Humalike is a product that adds social intelligence to AI agents, making them more human-like in interactions.
This paper introduces a new benchmark for evaluating social intelligence in AI systems, measuring their ability to understand and respond to social cues and interactions.
This paper presents OSCToM, an RL-guided method for generating adversarial data to test nested belief conflicts in LLMs, improving Theory of Mind reasoning on benchmarks like FANToM.
SAVOIR framework applies cooperative game theory and Shapley values to train language agents with improved social intelligence, achieving SOTA on SOTOPIA benchmark and matching GPT-4o performance.