OracleProto: A Reproducible Framework for Benchmarking LLM Forecasting via Knowledge Cutoffs and Temporal Masking

arXiv:2605.03762 · cs.AI · Submitted 2026-05-05 · Read on arXiv

cs.AI

Submitted: 2026-05-05

Updated: 2026-10-13

Terminology

• Benchmark — 2× in this paper · explained in 2 episodes
• Benchmarking — 1× in this paper · explained in 4 episodes

Sources

• Scaling Open-Ended Reasoning to Predict the Future
• Approaching Human-Level Forecasting with Language Models
• ForecastBench: A Dynamic Benchmark of AI Forecasting Capabilities
• Simulated Ignorance Fails: A Systematic Study of LLM Behaviors on Forecasting Problems Before Model Knowledge Cutoff
• Time-R1: Towards Comprehensive Temporal Reasoning in LLMs
• Agentic Forecasting with Structured Linguistic Beliefs
• Pitfalls in Evaluating Language Model Forecasters
• Outcome-based Reinforcement Learning to Predict the Future
• MIRAI: Evaluating LLM Agents for Event Forecasting
• FutureX: An Advanced Live Benchmark for LLM Agents in Future Prediction

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems