# Scaling Open-Ended Reasoning to Predict the Future

arXiv: https://arxiv.org/abs/2512.25070 · HTML: https://mlsanity.com/paper/2512.25070/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Placed in Time series reasoning, one of 17 directions in LLM reasoning.
- Builds on 22 of its 91 references that are in the map.
- First posted on arXiv 31 Dec 2025.

## Placed in

- LLM reasoning / [Time series reasoning](https://mlsanity.com/lr/time-series-reasoning/)

## Builds on (most cited first, 22 of 22)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [Decoupled Weight Decay Regularization](https://mlsanity.com/paper/1711.05101/) (2017)
- [Humanity's Last Exam](https://mlsanity.com/paper/2501.14249/) (2025)
- [Measuring short-form factuality in large language models](https://mlsanity.com/paper/2411.04368/) (2024)
- [Beyond Binary Rewards: Training LMs to Reason About Their Uncertainty](https://mlsanity.com/paper/2507.16806/) (2025)
- [ForecastBench: A Dynamic Benchmark of AI Forecasting Capabilities](https://mlsanity.com/paper/2409.19839/) (2024)
- [Approaching Human-Level Forecasting with Language Models](https://mlsanity.com/paper/2402.18563/) (2024)
- [Forecasting Future World Events with Neural Networks](https://mlsanity.com/paper/2206.15474/) (2022)
- [FutureX: An Advanced Live Benchmark for LLM Agents in Future Prediction](https://mlsanity.com/paper/2508.11987/) (2025)
- [Consent in Crisis: The Rapid Decline of the AI Data Commons](https://mlsanity.com/paper/2407.14933/) (2024)
- [ForecastQA: A Question Answering Challenge for Event Forecasting with Temporal Text Data](https://mlsanity.com/paper/2005.00792/) (2020)
- [Answer Matching Outperforms Multiple Choice for Language Model Evaluation](https://mlsanity.com/paper/2507.02856/) (2025)
- [Consistency Checks for Language Model Forecasters](https://mlsanity.com/paper/2412.18544/) (2024)
- [Pitfalls in Evaluating Language Model Forecasters](https://mlsanity.com/paper/2506.00723/) (2025)
- [Outcome-based Reinforcement Learning to Predict the Future](https://mlsanity.com/paper/2505.17989/) (2025)
- [Are LLMs Prescient? A Continuous Evaluation using Daily News as the Oracle](https://mlsanity.com/paper/2411.08324/) (2024)
- [LLMs Can Teach Themselves to Better Predict the Future](https://mlsanity.com/paper/2502.05253/) (2025)
- [OpenEP: Open-Ended Future Event Prediction](https://mlsanity.com/paper/2408.06578/) (2024)

## Built on by (most cited first, 21 of 21)

- [Agentic Forecasting using Sequential Bayesian Updating of Linguistic Beliefs](https://mlsanity.com/paper/2604.18576/) (2026)
- [KellyBench: A Benchmark for Long-Horizon Sequential Decision Making](https://mlsanity.com/paper/2604.27865/) (2026)
- [Aligning LLMs with Human Uncertainty: A Beta-Bernoulli Calibrator for LLM Forecasting](https://mlsanity.com/paper/2605.27668/) (2026)
- [Revealed Rationality: Label-Free Evaluation and Regularization from Representation Theorems](https://mlsanity.com/paper/2608.05015/) (2026)
- [OracleProto: A Reproducible Framework for Benchmarking LLM Forecasting via Knowledge Cutoffs and Temporal Masking](https://mlsanity.com/paper/2605.03762/) (2026)
- [Teaching Language Models to Forecast Research Success Through Comparative Idea Evaluation](https://mlsanity.com/paper/2605.21491/) (2026)
- [Dr-CiK: A Benchmark testing Deep Research for Context-Aided Forecasting](https://mlsanity.com/paper/2605.27904/) (2026)
- [Agentic Time Machine as an Infrastructure for Future-Event Forecasting](https://mlsanity.com/paper/2606.21013/) (2026)
- [What LLM Forecasters Know but Don't Say: Probing Internal Representations for Calibration and Faithfulness](https://mlsanity.com/paper/2607.08046/) (2026)
- [YC Bench: a Live Benchmark for Forecasting Startup Outperformance in Y Combinator Batches](https://mlsanity.com/paper/2604.02378/) (2026)
- [Harnessing Pre-Resolution Signals for Future Prediction Agents](https://mlsanity.com/paper/2604.15719/) (2026)
- [Reinforcement Learning over Predictive Distributions for LLM Regression](https://mlsanity.com/paper/2605.20740/) (2026)
- [Hindcast: Replaying Prediction Markets to Evaluate LLM Forecasters](https://mlsanity.com/paper/2607.14051/) (2026)
- [QuantSightBench: Evaluating LLM Quantitative Forecasting with Prediction Intervals](https://mlsanity.com/paper/2604.15859/) (2026)
- [GPU Forecasters: Language Models as Selective Surrogates for Kernel Runtime Optimization](https://mlsanity.com/paper/2605.31464/) (2026)
- [Fund2Persona: A Framework for Building and Refining Financial Advisor Personas from Fund Disclosure Data](https://mlsanity.com/paper/2606.29793/) (2026)
- [Diverse Evidence, Better Forecasts: Multi-Agent Deliberation Under Information Asymmetry](https://mlsanity.com/paper/2607.01661/) (2026)
- [From Narrative to Auditable Forecasts: A Structured Scaffold for Agentic Forecasting](https://mlsanity.com/paper/2609.05905/) (2026)
- [Forecast-Dojo: Replayable Environments for Benchmarking and Training LLM Forecasting Agents](https://mlsanity.com/paper/2609.28876/) (2026)
- [CHAIN: Calibrated LLM Forecasting via Causal-Temporal Hypergraph Inference](https://mlsanity.com/paper/2609.36689/) (2026)
- [Training Language Models to Fail Gracefully](https://mlsanity.com/paper/2610.20401/) (2026)

## Abstract (arXiv)

High-stakes decision making involves reasoning under uncertainty about the future. In this work, we train language models to make predictions on open-ended forecasting questions. To scale up training data, we synthesize novel forecasting questions from global events reported in daily news, using a fully automated, careful curation recipe. We train the Qwen3 thinking models on our dataset, OpenForesight. To prevent leakage of future information during training and evaluation, we use an offline news corpus, both for data generation and retrieval in our forecasting system. Guided by a small validation set, we show the benefits of retrieval, and an improved reward function for reinforcement learning (RL). Once we obtain our final forecasting system, we perform held-out testing between May to August 2025. Our specialized model, OpenForecaster 8B, matches much larger proprietary models, with our training improving the accuracy, calibration, and consistency of predictions. We find calibration improvements from forecasting training generalize across popular benchmarks. We open-source all our models, code, and data to make research on language model forecasting broadly accessible.