Wisdom Of The (AI) Crowd: Investigating Artificial Swarm Intelligence In Large Language Models

• URL: http://arxiv.org/abs/2606.31404v1
• Date: Tue, 30 Jun 2026 09:30:53 GMT
• Title: Wisdom Of The (AI) Crowd: Investigating Artificial Swarm Intelligence In Large Language Models
• Abstract summary: We investigate whether large language models (LLMs) can approximate swarm intelligence effects through artificial swarms.<n>We conducted a controlled experiment with 960 manually executed prompts across three proprietary models.<n>Results reveal consistent error reduction through intra- and inter-model aggregation, with significant error reductions up to 37 percentage points in MAPE.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• 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 $ρ=0.242-0.568$, 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.

Related papers

• Automated Generation of Complexity-Validated Decision Scenarios Using Large Language Models [1.6249267147413524]
  Decision-making research depends on diverse scenarios with carefully controlled complexity.<n>We developed an automated pipeline that uses LLms to generate structured decision scenarios.<n>We evaluated 4,238 scenarios across multiple domains and complexity tiers.
  arXiv  Detail & Related papers  (2026-08-09T17:12:48Z)
• ActTraitBench: Quantifying the Knowledge-Decision Gap in Large Language Models via Human-Grounded Behavioral Validation [8.82034003345674]
  Large Language Models (LLMs) can convincingly simulate personas in explicit self-reports, but often deviate in implicit behavioral decisions.<n>Existing benchmarks struggle to measure this asymmetry due to limited construct validity, multi-dimensional entanglement, and distributional biases.<n>We propose ActTraitBench, a human-grounded evaluation framework for measuring personality consistency in LLMs.
  arXiv  Detail & Related papers  (2026-05-28T11:40:35Z)
• Wisdom of LLM Crowds: Aggregation and Contamination in Language Model Ensembles [0.0]
  The wisdom of crowds -- the finding that aggregating judgments across individuals often outperforms the best individual -- has been extensively studied with human forecasters.<n>We elicited probability estimates from 15 large language models (LLMs) on 254 binary prediction market questions.<n>LLMs remained substantially less accurate, indicating a genuine gap in collective information aggregation.
  arXiv  Detail & Related papers  (2026-05-26T16:07:01Z)
• How Independent are Large Language Models? A Statistical Framework for Auditing Behavioral Entanglement and Reweighting Verifier Ensembles [46.63622714488747]
  Shared pretraining data, distillation, and alignment pipelines can induce hidden behavioral dependencies, latent entanglement.<n>In practice, this manifests as correlated reasoning patterns and synchronized failures.<n>We develop a statistical framework for auditing behavioral entanglement among black-box language models.
  arXiv  Detail & Related papers  (2026-04-08T23:32:06Z)
• DiscoUQ: Structured Disagreement Analysis for Uncertainty Quantification in LLM Agent Ensembles [5.647839536820347]
  We introduce DiscoUQ, a framework that extracts and leverages the structure of inter-agent disagreement to produce well-calibrated confidence estimates.<n>DiscoUQ-LLM achieves an average AUROC of 0.802, outperforming the best baseline.<n>The learned features generalize across benchmarks with near-zero performance degradation.
  arXiv  Detail & Related papers  (2026-03-21T23:24:12Z)
• Information Fidelity in Tool-Using LLM Agents: A Martingale Analysis of the Model Context Protocol [69.11739400975445]
  We introduce the first theoretical framework for analyzing error accumulation in Model Context Protocol (MCP) agents.<n>We show that cumulative distortion exhibits linear growth and high-probability deviations bounded by $O(sqrtT)$.<n>Key findings include: semantic weighting reduces distortion by 80%, and periodic re-grounding approximately every 9 steps suffices for error control.
  arXiv  Detail & Related papers  (2026-02-10T21:08:53Z)
• Adversarial Question Answering Robustness: A Multi-Level Error Analysis and Mitigation Study [0.0]
  Question answering (QA) systems achieve impressive performance on standard benchmarks like SQuAD, but remain vulnerable to adversarial examples.<n>This project investigates the adversarial robustness of transformer models on the AddSent adversarial dataset.
  arXiv  Detail & Related papers  (2026-01-06T04:20:33Z)
• MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling [115.74855199827596]
  MiroThinker is an open-source research agent designed to advance tool-augmented reasoning and information-seeking capabilities.<n>Unlike previous agents that only scale up model size or context length, MiroThinker explores interaction scaling at the model level.
  arXiv  Detail & Related papers  (2025-11-14T18:52:07Z)
• Evaluating & Reducing Deceptive Dialogue From Language Models with Multi-turn RL [64.3268313484078]
  Large Language Models (LLMs) interact with millions of people worldwide in applications such as customer support, education and healthcare.<n>Their ability to produce deceptive outputs, whether intentionally or inadvertently, poses significant safety concerns.<n>We investigate the extent to which LLMs engage in deception within dialogue, and propose the belief misalignment metric to quantify deception.
  arXiv  Detail & Related papers  (2025-10-16T05:29:36Z)
• Truth in the Few: High-Value Data Selection for Efficient Multi-Modal Reasoning [71.3533541927459]
  We propose a novel data selection paradigm termed Activation Reasoning Potential (RAP)<n>RAP identifies cognitive samples by estimating each sample's potential to stimulate genuine multi-modal reasoning.<n>Our RAP method consistently achieves superior performance using only 9.3% of the training data, while reducing computational costs by over 43%.
  arXiv  Detail & Related papers  (2025-06-05T08:40:24Z)
• Predictor-Corrector Enhanced Transformers with Exponential Moving Average Coefficient Learning [73.73967342609603]
  We introduce a predictor-corrector learning framework to minimize truncation errors. We also propose an exponential moving average-based coefficient learning method to strengthen our higher-order predictor. Our model surpasses a robust 3.8B DeepNet by an average of 2.9 SacreBLEU, using only 1/3 parameters.
  arXiv  Detail & Related papers  (2024-11-05T12:26:25Z)
• LLM Robustness Against Misinformation in Biomedical Question Answering [50.98256373698759]
  The retrieval-augmented generation (RAG) approach is used to reduce the confabulation of large language models (LLMs) for question answering. We evaluate the effectiveness and robustness of four LLMs against misinformation in answering biomedical questions.
  arXiv  Detail & Related papers  (2024-10-27T16:23:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.