Wisdom Of The (AI) Crowd: Investigating Artificial Swarm Intelligence In Large Language Models
Summary
This paper investigates whether LLMs can approximate swarm intelligence effects through intra- and inter-model aggregation, finding significant error reductions up to 37 percentage points in MAPE across eight estimation tasks.
View Cached Full Text
Cached at: 07/01/26, 05:38 AM
# Wisdom Of The (AI) Crowd: Investigating Artificial Swarm Intelligence In Large Language Models Source: [https://arxiv.org/abs/2606.31404](https://arxiv.org/abs/2606.31404) [View PDF](https://arxiv.org/pdf/2606.31404) > Abstract:Human swarm intelligence demonstrates remarkable collective accuracy but faces scalability constraints in cost, coordination, and time\. We investigate whether large language models \(LLMs\) can approximate swarm intelligence effects through artificial swarms, addressing a critical gap in understanding AI\-based aggregation mechanisms\. We conducted a controlled experiment with 960 manually executed prompts across three proprietary models \(GPT\-5, Gemini 2\.5 Pro, Claude Sonnet 4\.5\), testing intra\-model sampling and inter\-model aggregation on eight estimation tasks\. Results reveal consistent error reduction through intra\- and inter\-model aggregation, with significant error reductions up to 37 percentage points in MAPE across different aggregation strategies\. We observed small to large effect sizes for positive correlations \(Spearman's $\\rho=0\.242\-0\.568$, all $p<0\.001$\) between relative confidence interval widths and relative estimation errors, suggesting LLMs possess metacognitive awareness when assessing uncertainty\. We discuss implications for research and practice, providing actionable insights for deploying LLM swarms in organizational decision\-making\. ## Submission history From: Justin Brenne \[[view email](https://arxiv.org/show-email/9f59cc5b/2606.31404)\] **\[v1\]**Tue, 30 Jun 2026 09:30:53 UTC \(549 KB\)
Similar Articles
Wisdom of LLM Crowds: Aggregation and Contamination in Language Model Ensembles
This paper investigates whether aggregating probability estimates from multiple LLMs exhibits a wisdom-of-crowds effect, finding that learned aggregators outperform individual models and that training cutoff contamination is a pervasive confound in such evaluations.
The Wisdom of Artificial Deliberative Crowds
This study adapts a human deliberation paradigm to large language models, finding that deliberation among diverse models reduces collective error and improves individual accuracy across multiple real-world domains, with diversity being crucial.
Can AI Guess What You Know? Performance Comparison of Large Language Models for Human Domain Knowledge Estimation From Communication Logs
This paper investigates whether LLMs can infer individual domain knowledge from long-term Slack logs, comparing seven models and finding Gemini 2.5 Flash achieves the lowest error, highlighting feasibility and limits of automated expertise mapping.
Artificial Intelligence Models Can Predict and Collaboratively Modulate Human Memory Search
This research explores how large language models can predict and enhance human semantic memory search, showing that LLMs can track human thought trajectories better than other humans and improve human memory processing through collaborative interactions.
(Towards) Scalable Reliable Automated Evaluation with Large Language Models
This paper proposes a scalable, domain-agnostic framework for automated LLM evaluation that uses pairwise comparisons by multiple LLMs and an Elo rating system to approximate expert judgments, reducing the need for human intervention.