Diversity is the Strength of the AI Crowd
For AI forecasting systems, this work provides a practical recipe to improve ensemble accuracy by prioritizing diversity over individual accuracy.
The paper studies how to ensemble off-the-shelf LLM forecasts to maximize accuracy on future world events, finding that combining accurate but diverse models (e.g., Grok 4) yields stronger ensembles than simply adding more forecasts from similar models.
Top AI forecasting systems are approaching superforecaster-level accuracy on future world events, but still rely primarily on off-the-shelf LLMs combined with forecasting-specific context gathering and scaffolding. We study how to improve this recipe through ensembling: given a fixed number of samples, which off-the-shelf model forecasts should be combined to maximize accuracy? On binary questions from the Metaculus AI Benchmark, we find that individual accuracy is not enough: many frontier LLMs make highly correlated predictions, limiting the value of additional forecasts from the same or similar models. Instead, the strongest ensembles combine accurate but diverse forecasters, with models such as \model{Grok 4} contributing disproportionately because their predictions are less correlated with other frontier LLMs. These results suggest that the strength of the AI crowd comes not from sampling more forecasts indiscriminately, but from combining forecasts across models with complementary errors, motivating forecasting systems that explicitly optimize for both model quality and diversity.