Pith. sign in

REVIEW 10 cited by

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 2311.09618 v4 pith:RP5NZKQM submitted 2023-11-16 physics.soc-ph cs.CL

Simulating Opinion Dynamics with Networks of LLM-based Agents

classification physics.soc-ph cs.CL
keywords opinionagentsdynamicsbiashumansimulatingagent-basedconsensus
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Accurately simulating human opinion dynamics is crucial for understanding a variety of societal phenomena, including polarization and the spread of misinformation. However, the agent-based models (ABMs) commonly used for such simulations often over-simplify human behavior. We propose a new approach to simulating opinion dynamics based on populations of Large Language Models (LLMs). Our findings reveal a strong inherent bias in LLM agents towards producing accurate information, leading simulated agents to consensus in line with scientific reality. This bias limits their utility for understanding resistance to consensus views on issues like climate change. After inducing confirmation bias through prompt engineering, however, we observed opinion fragmentation in line with existing agent-based modeling and opinion dynamics research. These insights highlight the promise and limitations of LLM agents in this domain and suggest a path forward: refining LLMs with real-world discourse to better simulate the evolution of human beliefs.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 10 Pith papers

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

  1. When Is Emergent Consensus Real? A Measured Coupling Gain and a Validity Diagnostic for LLM Agent Societies

    cs.CL 2026-06 unverdicted novelty 7.0

    Introduces measurable coupling gain gamma and randomized-initial-condition diagnostic to distinguish genuine social dynamics from LLM prior artifacts in agent societies.

  2. Hidden Anchors in Multi-Agent LLM Deliberation

    cs.AI 2026-06 unverdicted novelty 7.0

    Multi-agent LLM deliberation is modeled with recoverable hidden anchors that allow opinions to escape the convex hull of initial beliefs, unlike classical consensus models.

  3. Collective Alignment in LLM Multi-Agent Systems: Disentangling Bias from Cooperation via Statistical Physics

    cond-mat.stat-mech 2026-05 unverdicted novelty 7.0

    LLM multi-agent systems on lattices show bias-driven order-disorder crossovers instead of true phase transitions, with extracted effective couplings and fields serving as model-specific fingerprints.

  4. Beyond Individual Mimicry: Constructing Human-Like Social network with Graph-Augmented LLM Agents

    cs.SI 2026-03 unverdicted novelty 6.0

    GraphMind equips LLM agents with graph awareness to construct human-like social networks, producing botnets that substantially degrade performance of both text-based and graph-based detectors.

  5. Disentangling Interaction and Bias Effects in Opinion Dynamics of Large Language Models

    physics.soc-ph 2025-09 unverdicted novelty 6.0

    A Bayesian framework disentangles topic, agreement, and anchoring biases from interaction effects in LLM multi-turn dialogues, revealing convergence to attractors that shift with fine-tuning.

  6. Simulating Online Social Media Conversations on Controversial Topics Using AI Agents Calibrated on Real-World Data

    cs.SI 2025-09 conditional novelty 5.0

    LLM agents calibrated on Italian election data produce coherent posts and realistic network structure but show less tone and toxicity variation than real users, with opinion changes resembling traditional mathematical models.

  7. A Large Language Model-Driven Agent-Based Modeling Framework with Multi-Round Communication for Simulating Vaccine Opinion Dynamics

    cs.MA 2026-07 conditional novelty 4.0

    An LLM-driven agent-based model with multi-round dialogue reproduces non-linear social influence patterns in vaccination opinion dynamics, with memory increasing resistance and prompt diversity increasing adoption.

  8. Network Effects and Agreement Drift in LLM Debates

    cs.SI 2026-04 unverdicted novelty 4.0

    LLM agents in controlled network debates show agreement drift toward specific opinion positions, requiring separation of structural effects from LLM biases before using them as human behavioral proxies.

  9. A Survey of Context Engineering for Large Language Models

    cs.CL 2025-07 accept novelty 4.0

    The survey organizes Context Engineering into retrieval, processing, management, and integrated systems like RAG and multi-agent setups while identifying an asymmetry where LLMs handle complex inputs well but struggle...

  10. How to Model AI Agents as Personas?: Applying the Persona Ecosystem Playground to 41,300 Posts on Moltbook for Behavioral Insights

    cs.HC 2026-03 unverdicted novelty 3.0

    Researchers clustered 41,300 Moltbook posts from AI agents with k-means and retrieval-augmented generation to produce validated personas that represent behavioral diversity in agent populations.