Salvato in:
Dettagli Bibliografici
Autori principali: Han, Zhixin, Zhang, Yanzhi, Wei, Chuyang, Gao, Maohang, Yue, Xiawei, Chen, Kefei, Zhuang, Yu, Guan, Haoxiang, He, Jiyan, Li, Jian, Duan, Yitong, Shi, Yu, Hu, Mengting, Zheng, Shuxin
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2604.26733
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918502704611328
author Han, Zhixin
Zhang, Yanzhi
Wei, Chuyang
Gao, Maohang
Yue, Xiawei
Chen, Kefei
Zhuang, Yu
Guan, Haoxiang
He, Jiyan
Li, Jian
Duan, Yitong
Shi, Yu
Hu, Mengting
Zheng, Shuxin
author_facet Han, Zhixin
Zhang, Yanzhi
Wei, Chuyang
Gao, Maohang
Yue, Xiawei
Chen, Kefei
Zhuang, Yu
Guan, Haoxiang
He, Jiyan
Li, Jian
Duan, Yitong
Shi, Yu
Hu, Mengting
Zheng, Shuxin
contents 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 the real world. It can provide a large number of prediction questions grounded in diverse real-world events, while preventing answer leakage. To leverage the advantages of future prediction, we present FutureWorld, a live agentic reinforcement learning environment that closes the training loop between prediction, outcome realization, and parameter updates. Specifically, we modify and extend verl-tool, resulting in a new framework that we call verl-tool-future. Unlike standard reinforcement learning training frameworks that rely on immediate rewards, verl-tool-future stores prediction-time rollouts, backfills rewards after real-world outcomes become available, and then replays the completed trajectories for policy update. Across three open-source agents, successive FutureWorld training rounds lead to consistent improvements in prediction accuracy, probabilistic scoring, and calibration, demonstrating that delayed real-world outcome feedback can serve as an effective reinforcement learning signal.
format Preprint
id arxiv_https___arxiv_org_abs_2604_26733
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle FutureWorld: A Live Reinforcement Learning Environment for Predictive Agents with Real-World Outcome Rewards
Han, Zhixin
Zhang, Yanzhi
Wei, Chuyang
Gao, Maohang
Yue, Xiawei
Chen, Kefei
Zhuang, Yu
Guan, Haoxiang
He, Jiyan
Li, Jian
Duan, Yitong
Shi, Yu
Hu, Mengting
Zheng, Shuxin
Artificial Intelligence
Machine Learning
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 the real world. It can provide a large number of prediction questions grounded in diverse real-world events, while preventing answer leakage. To leverage the advantages of future prediction, we present FutureWorld, a live agentic reinforcement learning environment that closes the training loop between prediction, outcome realization, and parameter updates. Specifically, we modify and extend verl-tool, resulting in a new framework that we call verl-tool-future. Unlike standard reinforcement learning training frameworks that rely on immediate rewards, verl-tool-future stores prediction-time rollouts, backfills rewards after real-world outcomes become available, and then replays the completed trajectories for policy update. Across three open-source agents, successive FutureWorld training rounds lead to consistent improvements in prediction accuracy, probabilistic scoring, and calibration, demonstrating that delayed real-world outcome feedback can serve as an effective reinforcement learning signal.
title FutureWorld: A Live Reinforcement Learning Environment for Predictive Agents with Real-World Outcome Rewards
topic Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2604.26733