arXiv cs.AI· Liqin Ye, Rongzhi Zhang, Xin Liu, Zheng Li, Yuan He, Qingyu Yin, Priyanka Nigam, Chao Zhang·· 12 小时前AI 评分34
AlphaBet：用强化学习训练 LLM 事件预测智能体
AlphaBet: Reinforcement Learning for LLM Event Forecasting Agents
AI 导读
AlphaBet 是一个智能体强化学习框架，训练单个 LLM 策略在多个预测日期上搜索、推理并报告概率，每个带日期的预测都用合适的评分规则对照最终结果打分。在 GLM-4.5-Air 上，AlphaBet 将 Forecast-Dojo 的 Brier 分数从 0.731 降至 0.626，FutureX 从 0.612 降至 0.528。
正文 · 原文
Abstract:Forecasting an unresolved event requires finding relevant evidence and deciding how strongly it supports each outcome. Yet outcome-based training of Large Language Model (LLM) forecasters often begins with preassembled evidence at a single prediction date, leaving evidence acquisition outside the learning loop. We introduce AlphaBet, an agentic reinforcement learning (RL) framework that trains a single LLM policy to search, reason, and report probabilities across multiple pre-resolution dates. Each dated forecast is scored by a proper scoring rule against the eventual outcome, allowing one resolved event to supervise decisions under different information states. We decompose forecasting regret into an evidence-acquisition gap and a probability-reporting gap, and show that Group Relative Policy Optimization (GRPO)'s standard-deviation normalization can distort the reporting target under multi-class proper scores. On GLM-4.5-Air, AlphaBet reduces the Brier score from 0.731 to 0.626 on Forecast-Dojo and from 0.612 to 0.528 on FutureX. Controlled ablations attribute these gains to multi-date training and show that they come from improvements in both information acquisition and probability reporting. Our empirical results validate that GRPO's std normalization degrades proper-scoring-rule performance while leaving top-outcome accuracy largely unchanged.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.22684 [cs.LG] |
| (or arXiv:2610.22684v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.22684 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Liqin Ye [view email]
[v1]
Thu, 15 Oct 2026 21:54:31 UTC (1,162 KB)
来源：arXiv cs.AI · arxiv.org