# Collective Innovation in Groups of Large Language Models

arXiv: https://arxiv.org/abs/2407.05377 · HTML: https://mlsanity.com/paper/2407.05377/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 52 references that are in the map.
- First posted on arXiv 7 Jul 2024.

## Builds on (most cited first, 15 of 15)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [Co-Writing Screenplays and Theatre Scripts with Language Models: An Evaluation by Industry Professionals](https://mlsanity.com/paper/2209.14958/) (2022)
- [The Debate Over Understanding in AI's Large Language Models](https://mlsanity.com/paper/2210.13966/) (2022)
- [Evaluating Cognitive Maps and Planning in Large Language Models with CogEval](https://mlsanity.com/paper/2309.15129/) (2023)
- [Can large language models explore in-context?](https://mlsanity.com/paper/2403.15371/) (2024)
- [Machine Culture](https://mlsanity.com/paper/2311.11388/) (2023)
- [Augmenting Autotelic Agents with Large Language Models](https://mlsanity.com/paper/2305.12487/) (2023)
- [WordCraft: An Environment for Benchmarking Commonsense Agents](https://mlsanity.com/paper/2007.09185/) (2020)
- [Cultural evolution in populations of Large Language Models](https://mlsanity.com/paper/2403.08882/) (2024)
- [Social Network Structure Shapes Innovation: Experience-sharing in RL with SAPIENS](https://mlsanity.com/paper/2206.05060/) (2022)
- [Improving Planning with Large Language Models: A Modular Agentic Architecture](https://mlsanity.com/paper/2310.00194/) (2023)

## Built on by (most cited first, 11 of 11)

- [Cultural Evolution of Cooperation among LLM Agents](https://mlsanity.com/paper/2412.10270/) (2024)
- [Can Machines Think Like Humans? A Behavioral Evaluation of LLM Agents in Dictator Games](https://mlsanity.com/paper/2410.21359/) (2024)
- [Position: We Need An Algorithmic Understanding of Generative AI](https://mlsanity.com/paper/2507.07544/) (2025)
- [The Society of HiveMind: Multi-Agent Optimization of Foundation Model Swarms to Unlock the Potential of Collective Intelligence](https://mlsanity.com/paper/2503.05473/) (2025)
- [Collaborative QA using Interacting LLMs. Impact of Network Structure, Node Capability and Distributed Data](https://mlsanity.com/paper/2511.14098/) (2025)
- [A Compositional Framework for Open-ended Intelligence](https://mlsanity.com/paper/2606.15386/) (2026)
- [GAI: Generative Agents for Innovation](https://mlsanity.com/paper/2412.18899/) (2024)
- [Evolutionary ecology of words](https://mlsanity.com/paper/2505.05863/) (2025)
- [On the Creativity of AI Agents](https://mlsanity.com/paper/2604.13242/) (2026)
- [Conversable Complexity: Agentic LLM Collectives as Interpretable Substrates](https://mlsanity.com/paper/2607.01047/) (2026)
- [Discovering Adaptive Transmission Programs for Collective Innovation](https://mlsanity.com/paper/2608.24545/) (2026)

## Abstract (arXiv)

Human culture relies on collective innovation: our ability to continuously explore how existing elements in our environment can be combined to create new ones. Language is hypothesized to play a key role in human culture, driving individual cognitive capacities and shaping communication. Yet the majority of models of collective innovation assign no cognitive capacities or language abilities to agents. Here, we contribute a computational study of collective innovation where agents are Large Language Models (LLMs) that play Little Alchemy 2, a creative video game originally developed for humans that, as we argue, captures useful aspects of innovation landscapes not present in previous test-beds. We, first, study an LLM in isolation and discover that it exhibits both useful skills and crucial limitations. We, then, study groups of LLMs that share information related to their behaviour and focus on the effect of social connectivity on collective performance. In agreement with previous human and computational studies, we observe that groups with dynamic connectivity out-compete fully-connected groups. Our work reveals opportunities and challenges for future studies of collective innovation that are becoming increasingly relevant as Generative Artificial Intelligence algorithms and humans innovate alongside each other.