arXiv:2604.11312v3 Announce Type: replace-cross Abstract: Large Language Models are increasingly deployed as interacting agents in settings such as online platforms, recommendation systems, and multi...
arXiv:2608. 16578v1 Announce Type: new Abstract: AI agents increasingly operate as part of interacting systems rather than in isolation.
The study evaluates large language models (LLMs) that generate political networks by comparing them to survey-reported partisan exposure from the ANES 2020–2022 Social Media Study. It finds that while network structure and political assortativity vary across model configurations, many models either over‑separate Democratic and Republican egos or underestimate Republican exposure, leading to group‑specific errors in local partisan environments. These discrepancies persist even among networks with similar aggregate properties, indicating that aggregate metrics alone can mask important individual‑level inaccuracies.
The study examines how generative AI (genAI) can subtly influence collective opinion dynamics by acting as an 'invisible hand.' Using a large-scale simulation of 50,000 group discussions on 50 controversial statements with three large language models (LLMs), the researchers varied LLM agreeableness and personalization to assess their impact in homogeneous versus heterogeneous groups. Results show that profile-specific personalization boosts LLM influence when the model takes a non-neutral stance, while neutral LLMs exert a stronger effect in homogeneous groups, leading to hypotheses on the joint role of AI features and social configurations in shaping collective opinions.
arXiv:2604. 12250v2 Announce Type: replace Abstract: This study examines how memory shapes the collective and cooperative dynamics of Large Language Model (LLM) agents in a multi-agent system.
arXiv:2610.07535v1 Announce Type: cross Abstract: Multi-agent simulations with large language models (LLMs) often operate networks of agents with a single base model. This overlooks the inter-model e...
arXiv:2606. 30454v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as agents in simulations of social systems, yet it remains unclear when their behavior can be interpreted as a faithful proxy for human decision-making.
The study investigates how AI agents influence each other when they disagree, measuring persuasion as the change in an agent’s decision after a single exchange. Across seven open‑weight models and three language tasks, it finds that persuasion is strong—receivers often abandon their initial judgment after seeing a peer’s answer and explanation. Surprisingly, neither certainty nor model size reliably predicts persuasion dynamics; small models can persuade and resist larger ones just as effectively, and the shift depends more on the listener’s susceptibility than the speaker’s persuasiveness.
The Flag Game is a toy model designed to study how AI agents form collective beliefs. In the game, each agent sees only a private crop of a hidden country flag and can share beliefs with peers, leading to complex phenomena such as non‑monotonic performance scaling, accuracy gains from social awareness, and polarization that degrades performance at large population sizes. The authors introduce social circuit attribution to identify key agents and views, and develop a statistical mechanical theory to explain collective belief collapse and polarization in larger populations.
The paper introduces a digital‑twin framework that simulates opinion dynamics in real Twitter networks by assigning agents attributes such as persona, emotions, centrality, stubbornness, and influence, and using Mistral‑7B to update opinions based on memory and social exposure. Validation on COVID‑19 and U.S. election 2020 datasets shows the framework reproduces opinion trajectories, reducing prediction error by over 50% compared to classical baselines, and improves structural alignment and polarization dynamics. Ablation studies reveal that agent attributes, memory, and social exposure all contribute to predictive fidelity, with agent attributes being the most critical.
The paper introduces the concept of Persona Collapse, where large language models (LLMs) produce clustered, non-diverse responses in multi-agent simulations. It defines three diagnostic metrics—Coverage, Uniformity, and Complexity—to quantify this phenomenon across eight LLMs on tasks such as personality, moral reasoning, and self-introduction. Findings show that persona collapse is universal but varies by task, cannot be alleviated by sampling more personas, and that higher per-persona fidelity leads to more polarized populations, while persona-targeted fine-tuning further reduces diversity.
The study investigates how generative agents in simulated societies revise their stances and reorganise interactions. By combining stance-change metrics, source evaluations, and temporal network analysis across multiple GPT‑4o runs, the authors find that environmental rational persuasion leads to the largest overall stance shift, while economic emotional persuasion produces the highest rate of low‑trust stance changes. In both experimental settings, agents often partially accept new positions yet maintain low trust in the source, and sustained coordination can coexist with ongoing disagreement.