ForecastBench-Sim: A Simulated-World Forecasting Benchmark
Quick Answer
ForecastBench-Sim introduces a simulated-world forecasting benchmark using Freeciv game rollouts, enabling continuous and binary forecasting tasks.
Quick Take
It allows for controlled evaluation of probabilistic reasoning in dynamic environments, addressing limitations of real-world benchmarks.
Key Points
- Utilizes game rollouts from Freeciv for benchmarking forecasting models.
- Enables continuous and binary forecasting questions across arbitrary time horizons.
- Facilitates scoring of counterfactual and causal questions in a simulated environment.
- Provides immediate resolution of rare or disruptive outcome examples.
- Aims to enhance understanding of probabilistic reasoning under dynamic conditions.
Paper Resources
📖 Reader Mode
~2 min readAbstract:Forecasting benchmarks for general-purpose AI systems usually inherit the constraints of the real world: outcomes resolve slowly, tail events are rare, and counterfactual questions are difficult to score. We introduce ForecastBench-Sim, a simulated-world forecasting benchmark built on game rollouts from Freeciv, a turn-based strategy game modelled on the Civilization series. Forecasters receive a fixed world report (a structured snapshot of the current game state) and answer questions about hidden future states; the benchmark then continues the simulation and scores forecasts. Because the world is simulated, the same setup can generate continuous or binary forecasting questions at arbitrary time horizons, paired intervention worlds for conditional or causal questions, and resolved examples of rare or disruptive outcomes. We describe the benchmark pipeline, question families, scoring protocol, and release artifacts, and report validation slices from model evaluations and an anonymized human pilot. ForecastBench-Sim is intended to complement real-world forecasting benchmarks by providing controlled, immediately resolvable tasks for studying probabilistic reasoning under dynamic world states.
| Comments: | 15 pages, 5 main figures, 6 appendix figures. Spotlight presentation at Forecasting as a New Frontier of Intelligence / Workshop on AI Forecasting, ICML 2026 |
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG) |
| Cite as: | arXiv:2606.18686 [cs.AI] |
| (or arXiv:2606.18686v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2606.18686 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Jaeho Lee [view email]
[v1]
Wed, 17 Jun 2026 04:52:41 UTC (1,986 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →HOBA: Hierarchical On-Policy Bidding Agents for Adaptive Online Advertising
HOBA (Hierarchical On-policy Bidding Agents) is a novel hierarchical reinforcement learning framework that enhances online advertising bidding systems by improving adaptability and reducing hyperparameter tuning costs. It utilizes a for hyperparameter inference, a SARSA agent for expert model selection, and a dynamic expert pool for bid execution, achieving a +3.6% increase in target cost during large-scale deployment and outperforming state-of-the-art baselines on AuctionNet.