FutureWorld: A Live Environment for Training Predictive Agents with Real-World Outcome Rewards
For researchers building agents that learn from real-world events, this work provides a unified environment for live future prediction, but the results are preliminary and the novelty is incremental.
The authors present FutureWorld, a live reinforcement learning environment for training predictive agents using real-world outcome rewards. Training open-source models over consecutive days showed effectiveness, and a daily benchmark established performance baselines for frontier agents.
Live future prediction refers to the task of making predictions about real-world events before they unfold. This task is increasingly studied using large language model-based agent systems, and it is important for building agents that can continually learn from real-world. Just as interactive environments have often driven progress in agents, advancing live future prediction naturally motivates viewing it as a learning environment. Prior works have explored future prediction from several different parts, but have generally not framed it as a unified learning environment. This task is appealing for learning because it can provide a large number of prediction questions grounded in diverse real-world events, while preventing answer leakage. To leverage the advantages of live future prediction, we present FutureWorld, a live agentic reinforcement learning environment that closes the training loop between prediction, outcome realization, and parameters update. In our environment, we take three open-source base models and train them for consecutive days. The results show that training is effective. Furthermore, we build a daily benchmark based on the environment and evaluate several frontier agents on it to establish performance baselines for current agent systems.