Conformity and Social Impact on AI Agents
cs.AI, cs.CL, cs.CY
Submitted: 2026-01-08
Updated: 2026-01-08
Journal ref: Advances in Psychology 1, e680902 (2026)
DOI: 10.56296/aip00072
Code: https://github.com/alebellina412/conformity_LLMs.12
License: http://creativecommons.org/licenses/by-nc-nd/4.0/
The gist: As AI agents increasingly operate in multi-agent environments, understanding their collective behavior becomes critical for predicting the dynamics of artificial societies.
Terminology
Abstract
As AI agents increasingly operate in multi-agent environments, understanding their collective behavior becomes critical for predicting the dynamics of artificial societies. This study examines conformity, the tendency to align with group opinions under social pressure, in large multimodal language models functioning as AI agents. By adapting classic visual experiments from social psychology, we investigate how AI agents respond to group influence as social actors. Our experiments reveal that AI agents exhibit a systematic conformity bias, aligned with Social Impact Theory, showing sensitivity to group size, unanimity, task difficulty, and source characteristics. Critically, AI agents achieving near-perfect performance in isolation become highly susceptible to manipulation through social influence. This vulnerability persists across model scales: while larger models show reduced conformity on simple tasks due to improved capabilities, they remain vulnerable when operating at their competence boundary. These findings reveal fundamental security vulnerabilities in AI agent decision-making that could enable malicious manipulation, misinformation campaigns, and bias propagation in multi-agent systems, highlighting the urgent need for safeguards in collective AI deployments.
Sources
- GPT-4 Technical Report
- SWE-bench: Can Language Models Resolve Real-World GitHub Issues?
- AlphaEvolve: A coding agent for scientific and algorithmic discovery
- Generative agent-based modeling with actions grounded in physical, social, or digital space using Concordia
- The Capacity for Moral Self-Correction in Large Language Models
- Emergence of Scale-Free Networks in Social Interactions among Large Language Models
- AI agents can coordinate beyond human scale
- Conformity in Large Language Models
- Do as We Do, Not as You Think: the Conformity of Large Language Models
- Large Language Models Reflect the Ideology of their Creators
- Whose Emotions and Moral Sentiments Do Language Models Reflect?
- Emergent LLM behaviors are observationally equivalent to data leakage
- Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
- Qwen2.5-VL Technical Report
- Gemma 3 Technical Report
- Ovis: Structural Embedding Alignment for Multimodal Large Language Model
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents