Social Agent Group
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
Defining and classifying models of groups: The social ontology of higher-order networks
arXiv:2507.02758v2 Announce Type: replace Abstract: In complex systems research, the study of higher-order interactions has exploded in recent years. Researchers have formalized various types of group interactions, such as public goods games, biological contagion, and information broadcasting, showing how higher-order networks can capture group effects more directly than pairwise models. However, equating hyperedges-edges involving more than two agents-with groups can be misleading, as it...
SAGE: A Quantitative Evaluation of Socialized Evolution in Agent Ecosystems
Announce Type: new Abstract: Self-improving language agents are typically evaluated in isolation: an agent attempts a task, receives feedback, and iteratively refines its own behavior. Yet agents increasingly operate alongside peers whose strategies and outcomes are publicly visible. This raises an under-studied question: when does shared experience produce improvements that self-improvement alone cannot achieve?
TriAlign: Towards Universal Truth Consistency in Personalized LLM Alignment
arXiv:2606.01755v1 Announce Type: new Abstract: Personalized large language models adapt responses to users' preferences and social attributes, but can introduce substantial universal truth inconsistencies across social groups, where some groups systematically receive less accurate responses on objective tasks. Existing alignment methods either ignore personalization or mainly focus on subjective preference alignment, largely overlooking fairness and consistency in universal truths. To...
EduMirror: Modeling Educational Social Dynamics with Value-driven Multi-agent Simulation
arXiv:2606.07948v1 Announce Type: new Abstract: Understanding how educational social dynamics evolve is critical for informing effective educational policies and counterfactual interventions. However, traditional methods face a fundamental dilemma: observational studies often lack causal power, while controlled experiments are frequently constrained by ethical concerns. Although LLM-based multi-agent simulations offer a scalable in silico alternative, existing approaches remain limited by...
On Leadership Emergence in Opinion Dynamics on Social Networks
Announce Type: new Abstract: Leadership in social groups emerges dynamically through interaction and opinion exchange. Empirical evidence indicates that individuals expressing strong opinions tend to gain influence, while sustained leadership critically depends on maintaining alignment with the surrounding social context. Motivated by these observations, we introduce a coupled dynamical model describing the simultaneous evolution of opinions and leadership in a networked population.
On Leadership Emergence in Opinion Dynamics on Social Networks
Announce Type: cross Abstract: Leadership in social groups emerges dynamically through interaction and opinion exchange. Empirical evidence indicates that individuals expressing strong opinions tend to gain influence, while sustained leadership critically depends on maintaining alignment with the surrounding social context. Motivated by these observations, we introduce a coupled dynamical model describing the simultaneous evolution of opinions and leadership in a networked population.
MASCOT: Towards Multi-Agent Socio-Collaborative Companion Systems
arXiv:2601.14230v2 Announce Type: replace Abstract: Multi-agent systems (MAS) are emerging as promising socio-collaborative companions for emotional and cognitive support. However, existing systems frequently suffer from persona collapse, where agents revert to generic, homogenized assistant behaviors, and social sycophancy, where agents produce redundant, non-constructive dialogue. We propose MASCOT, a multi-agent framework for multi-perspective socio-collaborative companions.
The Social Cost of Intelligence: Emergence, Propagation, and Amplification of Stereotypical Bias in Multi-Agent Systems
arXiv:2510.10943v2 Announce Type: replace Abstract: Bias in large language models (LLMs) remains a persistent challenge, often leading to stereotyping and unfair treatment across social groups. While prior work has mainly focused on individual LLMs, the emergence of multi-agent systems (MAS), where multiple LLMs collaborate and communicate, introduces new and underexplored dynamics in how bias emerges, propagates, and amplifies. To systematically investigate these dynamics, we propose a...
Dueling protests face off at New Jersey ICE detention center over detainee conditions
Tensions rose at a Newark, New Jersey, immigration detention center on Saturday as a group of pro-ICE protesters faced off with demonstrators who have maintained a presence outside the facility for more than a week in support of detainees who they say are enduring inhumane conditions inside. Saturday morning’s protests outside the Delaney Hall facility saw a heavy police presence, including a group of officers with riot shields blocking the entrance. At one point, a group of federal agents,...
Private Noise and Public Error in Collective Information Acquisition
Announce Type: cross Abstract: Collective information acquisition requires groups to combine personal evidence with social information while remaining coupled to the external state. Communication noise can affect this process, but the role of noise remains unclear. In an online experiment, 600 participants worked in four-person human groups estimating a room temperature across 25 rounds while receiving either faithful social information, comprehension noise in which each receiver saw...