Pith. sign in

REVIEW 5 cited by

Emergence of human-like polarization among large language model agents

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2501.05171 v2 pith:6CY5ZLC5 submitted 2025-01-09 cs.SI cs.CY

classification cs.SIcs.CY
keywords agentspolarizationhuman-likelanguagelargemechanismssocialbehaviours
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Rapid advances in large language models (LLMs) have not only empowered autonomous agents to generate social networks, communicate, and form shared and diverging opinions on political issues, but have also begun to play a growing role in shaping human political deliberation. Our understanding of their collective behaviours and underlying mechanisms remains incomplete, however, posing unexpected risks to human society. In this paper, we simulate a networked system involving thousands of large language model agents, discovering their social interactions, guided through LLM conversation, result in human-like polarization. We discover that these agents spontaneously develop their own social network with human-like properties, including homophilic clustering, but also shape their collective opinions through mechanisms observed in the real world, including the echo chamber effect. Similarities between humans and LLM agents -- encompassing behaviours, mechanisms, and emergent phenomena -- raise concerns about their capacity to amplify societal polarization, but also hold the potential to serve as a valuable testbed for identifying plausible strategies to mitigate polarization and its consequences.

Discussion (0). Sign in to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. CrimeMind: Simulating Urban Crime with Multi-Modal LLM Agents

    cs.AI 2025-06 conditional novelty 7.0 of 10

    An LLM-driven agent-based model that integrates Routine Activity Theory and street-view safety perception outperforms baselines in simulating urban crime hotspots across four U.S. cities.

  2. AgentSociety 2: An Integrated Research Environment for Executable Social Science

    cs.CY 2026-06 unverdicted novelty 6.0 of 10

    An integrated LLM-agent environment runs social-science experiments from hypothesis to manuscript, reproducing several known human patterns while failing on others (implicit self-bias, free-riding decay, norm collapse).

  3. Emergent Coordinated Behaviors in Networked LLM Agents: Modeling the Strategic Dynamics of Information Operations

    cs.MA 2025-10 conditional novelty 6.0 of 10

    In networked LLM agents, simply informing influence-operation agents of their teammates' identities produces coordination nearly as strong as collective deliberation and voting.

  4. Fine-Grained Interpretation of Political Opinions in Large Language Models

    cs.CL 2025-06 conditional novelty 6.0 of 10

    Four-dimensional political concept vectors learned from LLM internals can detect and partially steer political leanings better than a single left-right axis.

  5. Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity

    cs.HC 2025-07 conditional novelty 5.0 of 10

    When LLMs are given more context about a real social media user, they become more ideologically consistent but also more extreme, toxic, and stereotyped than the user actually is.

Pith tools