作者位次 #5/12ACL 2026Findings· Findings of ACL
GR 1: Reinforcement-Enhanced LLM for Geoscience Reasoning
Yule Xie · Jiaxin Ding · Cheng Deng · Shiqing Gao · Junran Zhang · Sibo Zhang · Zeyuan Wang · Ke Wu · Xin Ding · Luoyi Fu · Meng Jin · Xinbing Wang
摘要
Reinforcement learning (RL) has recently shown remarkable ability to enhance reasoning in large language models (LLMs), yet its potential in scientific domains beyond mathematics remains largely unexplored. Geoscience questions couple broad factual knowledge with multi-step inference and often re...