arXiv AI
MASCOT: Multi-Agent Socio-Collaborative Companion Systems
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Jun 2
MASCOT: Towards Multi-Agent Socio-Collaborative Companion Systems
arXiv:2601. 14230v2 Announce Type: replace-cross Abstract: Multi-agent systems (MAS) are emerging as promising socio-collaborative companions for emotional and cognitive support.
arXiv Computation and Language
Sep 30
AnthroDial: Benchmarking LLM Anthropomorphism in Autonomous Social Interaction
arXiv:2609.37853v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed as social agents, yet credible human-like interaction requires more than fluent responses or per...
arXiv Computation and Language
Sep 22
Deep Persona: A Psychologically Grounded Architecture and Evaluation Framework for Role-Playing Agents and Simulations
arXiv:2609.22255v1 Announce Type: new Abstract: Existing approaches to persona simulation with Large Language Models (LLMs) mostly rely on shallow character descriptions that fail to sustain coherent...
arXiv AI
Jul 10
From Triggers to Emotions: A CPM-Grounded Appraisal Multi-Agent for Dynamic Emotional Evolution in Persona-Based Dialogue
arXiv:2607. 07824v1 Announce Type: cross Abstract: Large Language Models (LLMs) have substantially advanced persona-based dialogue agents for emotion-sensitive role simulation in healthcare, education, counseling, customer service, and interactive storytelling.
arXiv AI
Oct 15
Agent Sociodrama: Social-Dynamics-Guided Persona Recasting for LLM Agent Teams
arXiv:2610.15788v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly deployed as teams, yet they fail in characteristically social ways: information holders stay silent,...
arXiv AI
Sep 24
Emergi-PersonaOS: A Persona Agent Operating System for Situational Adaptation and Controllable Evolution
Emergi-PersonaOS is a psychology‑grounded operating system designed to manage persona agents throughout their lifecycle. It structures personas into three layers—dispositional traits, characteristic adaptations, and narrative identity—allowing the system to infer current persona states from situational cues and generate appropriate actions. The OS records experiences, evaluates revision candidates, and controls belief updates through explicit review and traceable evidence, enabling controllable evolution of persona agents over long interactions.