Paper Detail
Liqin Ye, Rongzhi Zhang, Xin Liu, Zheng Li, Yuan He, Qingyu Yin, Priyanka Nigam, Chao Zhang
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.
No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.
No ranking explanation is available yet.
No tags.
@misc{ye2026alphabet,
title = {AlphaBet: Reinforcement Learning for LLM Event Forecasting Agents},
author = {Liqin Ye and Rongzhi Zhang and Xin Liu and Zheng Li and Yuan He and Qingyu Yin and Priyanka Nigam and Chao Zhang},
year = {2026},
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. E},
url = {https://huggingface.co/papers/2610.22684},
keywords = {agentic reinforcement learning, Group Relative Policy Optimization, proper scoring rule, Brier score, multi-date training, evidence acquisition, probability reporting, code available, huggingface daily},
eprint = {2610.22684},
archiveprefix = {arXiv},
}
{}