跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 2026-10-15AI 評分46

AlphaBet:以強化學習訓練 LLM 事件預測智能體

AlphaBet: Reinforcement Learning for LLM Event Forecasting Agents

AI 導讀

AlphaBet 以智能體式強化學習訓練單一 LLM 策略,讓其跨多個預測日期搜尋證據、推理並報告事件結果機率,降低 Brier 評分。使用 GLM-4.5-Air 時,Forecast-Dojo 的 Brier 評分由 0.731 降至 0.626,FutureX 則由 0.612 降至 0.528。

正文

Published on Oct 15

Authors:

,

,

,

,

,

,

Abstract

AlphaBet uses agentic reinforcement learning to train a single LLM policy to search, reason, and report forecast probabilities across multiple dates, reducing Brier scores by improving both evidence acquisition and probability reporting.

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.

View arXiv page View PDF Project page GitHub 3 Add to collection

Get this paper in your agent:

hf papers read 2610.22684

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2610.22684 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2610.22684 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2610.22684 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co