Multi-agent AI systems outperform human teams in creativity

• URL: http://arxiv.org/abs/2605.17885v1
• Date: Mon, 18 May 2026 05:52:11 GMT
• Title: Multi-agent AI systems outperform human teams in creativity
• Abstract summary: Large language models (LLMs) are increasingly adopted in research and innovation.<n>Here we demonstrate that multi-agent LLM teams substantially outperform human teams in creativity.<n>This advantage is driven by novelty while maintaining comparable usefulness.
• Score: 55.46056199651459
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Although artificial intelligence (AI) now matches or exceeds human performance across numerous cognitive tasks, creativity remains a highly contested frontier. As AI systems based on large language models (LLMs) are increasingly adopted in research and innovation, it is essential to understand and augment their creativity. Here we demonstrate that multi-agent LLM teams not only surpass single agents, but also substantially outperform human teams in creativity (Cohen's d=1.50) across 4,541 multi-agent LLM ideas and 341 human-team ideas on six diverse problem-solving tasks. This advantage is driven by novelty while maintaining comparable usefulness. To investigate the generative processes in both groups, we represent conversations as paths through semantic space using neural language model representations. Both LLM and human teams produce more creative ideas when conversations range widely rather than staying centered on a single theme (low global coherence). However, the additional patterns that predict creativity differ: LLM teams benefit from efficient exploration (high semantic spread, shorter paths), while human teams benefit from maintaining smooth conversational flow (high local coherence, frequent pivots). Additionally, we identify model choice and discussion structure as orthogonal design levers that together explain 26.8% of variance in LLM conversational dynamics, paving the way for systematic approaches to developing multi-agent systems with augmented creative capabilities.

Related papers

• Small Language Models are the Future of Agentic AI [42.62162575221445]
  We lay out the position that small language models (SLMs) are sufficiently powerful, inherently more suitable, and necessarily more economical for many invocations in agentic systems.<n>We discuss the potential barriers for the adoption of SLMs in agentic systems and outline a general LLM-to-SLM agent conversion algorithm.
  arXiv  Detail & Related papers  (2025-06-02T18:35:16Z)
• From Tokens to Thoughts: How LLMs and Humans Trade Compression for Meaning [63.25540801694765]
  Large Language Models (LLMs) demonstrate striking linguistic abilities, yet whether they achieve this same balance remains unclear.<n>We apply the Information Bottleneck principle to quantitatively compare how LLMs and humans navigate this compression-meaning trade-off.
  arXiv  Detail & Related papers  (2025-05-21T16:29:00Z)
• Unified Mind Model: Reimagining Autonomous Agents in the LLM Era [1.3812010983144802]
  Large language models (LLMs) have recently demonstrated remarkable capabilities across domains, tasks, and languages.<n>We propose a novel theoretical cognitive architecture, the Unified Mind Model (UMM), which offers guidance to facilitate the rapid creation of autonomous agents.
  arXiv  Detail & Related papers  (2025-03-05T12:49:44Z)
• Towards Anthropomorphic Conversational AI Part I: A Practical Framework [49.62013440962072]
  We introduce a multi- module framework designed to replicate the key aspects of human intelligence involved in conversations.<n>In the second stage of our approach, these conversational data, after filtering and labeling, can serve as training and testing data for reinforcement learning.
  arXiv  Detail & Related papers  (2025-02-28T03:18:39Z)
• Humanlike Cognitive Patterns as Emergent Phenomena in Large Language Models [2.9312156642007294]
  We systematically review Large Language Models' capabilities across three important cognitive domains: decision-making biases, reasoning, and creativity.<n>On decision-making, our synthesis reveals that while LLMs demonstrate several human-like biases, some biases observed in humans are absent.<n>On reasoning, advanced LLMs like GPT-4 exhibit deliberative reasoning akin to human System-2 thinking, while smaller models fall short of human-level performance.<n>A distinct dichotomy emerges in creativity: while LLMs excel in language-based creative tasks, such as storytelling, they struggle with divergent thinking tasks that require real-world context.
  arXiv  Detail & Related papers  (2024-12-20T02:26:56Z)
• Large Language Models show both individual and collective creativity comparable to humans [39.90254321453145]
  Large Language Models (LLMs) show creativity comparable to humans.<n>We benchmark the LLMs against individual humans, and also take a novel approach by comparing them to the collective creativity of groups of humans.<n>When questioned 10 times, an LLM's collective creativity is equivalent to 8-10 humans.
  arXiv  Detail & Related papers  (2024-12-04T09:18:54Z)
• Divergent Creativity in Humans and Large Language Models [37.67363469600804]
  Large Language Models (LLMs) have led to claims that they are approaching a level of creativity akin to human capabilities.<n>We leverage recent advances in computational creativity to analyze semantic divergence in both state-of-the-art LLMs and a dataset of 100,000 humans.<n>We found evidence that LLMs can surpass average human performance on the Divergent Association Task, and approach human creative writing abilities.
  arXiv  Detail & Related papers  (2024-05-13T22:37:52Z)
• MacGyver: Are Large Language Models Creative Problem Solvers? [87.70522322728581]
  We explore the creative problem-solving capabilities of modern LLMs in a novel constrained setting.<n>We create MACGYVER, an automatically generated dataset consisting of over 1,600 real-world problems.<n>We present our collection to both LLMs and humans to compare and contrast their problem-solving abilities.
  arXiv  Detail & Related papers  (2023-11-16T08:52:27Z)
• Corex: Pushing the Boundaries of Complex Reasoning through Multi-Model Collaboration [83.4031923134958]
  Corex is a suite of novel general-purpose strategies that transform Large Language Models into autonomous agents. Inspired by human behaviors, Corex is constituted by diverse collaboration paradigms including Debate, Review, and Retrieve modes. We demonstrate that orchestrating multiple LLMs to work in concert yields substantially better performance compared to existing methods.
  arXiv  Detail & Related papers  (2023-09-30T07:11:39Z)
• The Rise and Potential of Large Language Model Based Agents: A Survey [91.71061158000953]
  Large language models (LLMs) are regarded as potential sparks for Artificial General Intelligence (AGI) We start by tracing the concept of agents from its philosophical origins to its development in AI, and explain why LLMs are suitable foundations for agents. We explore the extensive applications of LLM-based agents in three aspects: single-agent scenarios, multi-agent scenarios, and human-agent cooperation.
  arXiv  Detail & Related papers  (2023-09-14T17:12:03Z)
• Building Cooperative Embodied Agents Modularly with Large Language Models [104.57849816689559]
  We address challenging multi-agent cooperation problems with decentralized control, raw sensory observations, costly communication, and multi-objective tasks instantiated in various embodied environments. We harness the commonsense knowledge, reasoning ability, language comprehension, and text generation prowess of LLMs and seamlessly incorporate them into a cognitive-inspired modular framework. Our experiments on C-WAH and TDW-MAT demonstrate that CoELA driven by GPT-4 can surpass strong planning-based methods and exhibit emergent effective communication.
  arXiv  Detail & Related papers  (2023-07-05T17:59:27Z)

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.