ACL 2026 | 时空数据（Spatial-Temporal）论文总结【LLM: Agent: 多模态大模型: POI推荐: 空间推理: 交通大模型: 气象Agent等】

ACL 2026将在2026年7月2日至7日于美国加利福尼亚州圣迭戈（San Diego, California, United States）举行。

本文总结了ACL 2026上有关时空数据（Spatial-Temporal）的相关论文，共计11篇，其中Main有8篇，Findings有4篇。如有疏漏，欢迎补充。

时空数据Topic：LLM，Agent，多模态大模型，POI推荐，空间推理，交通大模型，气象Agent等

Main1. Reasoning Over Space: Enabling Geographic Reasoning for LLM-Based Generative Next POI Recommendation2. CityCube: Benchmarking Cross-view Spatial Reasoning on Vision-Language Models in Urban Environments3. STReasoner: Empowering LLMs for Spatio-Temporal Reasoning in Time Series via Spatial-Aware Reinforcement Learning4. Traffic-R1: Reinforced LLMs Bring Human-Like Reasoning to Traffic Signal Control Systems5. TransLLM: A Unified Multi-Task Large Language Model for Urban Transportation via Learnable Prompting6. UrbanGeoEval: A City-Scale Benchmark for Evaluating Large Language Models in Geospatial Reasoning7. GCA Framework: A GCC Countries–Grounded Dataset and Agentic Pipeline for Climate Decision Support8. Spatial-Agent: Agentic Geo-spatial Reasoning with Scientific Core ConceptsFindings9. Spatial-RAG: Spatial Retrieval Augmented Generation for Real-World Geospatial Reasoning Questions10. ClimAgent: LLM as Agents for Autonomous Open-ended Climate Science Analysis11. ClimateCause: Complex and Implicit Causal Structures in Climate Reports

Main

1 Reasoning Over Space: Enabling Geographic Reasoning for LLM-Based Generative Next POI Recommendation

链接：https://aclanthology.org/2026.acl-long.332/

作者：Dongyi Lv, Qiuyu Ding, Heng-Da Xu, Zhaoxu Sun, Zhi Wang, Feng Xiong, Mu Xu

关键词：POI推荐，LLM，生成式推荐

2 CityCube: Benchmarking Cross-view Spatial Reasoning on Vision-Language Models in Urban Environments

链接：https://aclanthology.org/2026.acl-long.416/

作者：Haotian Xu, Yue Hu, Zhengqiu Zhu, Chen Gao, Ziyou Wang, Junreng Rao, Wenhao Lu, Weishi Li, Quanjun Yin, Yong Li

关键词：benchmark，空间推理，VLM

3 STReasoner: Empowering LLMs for Spatio-Temporal Reasoning in Time Series via Spatial-Aware Reinforcement Learning

链接：https://aclanthology.org/2026.acl-long.702/

作者：Juntong Ni, Shiyu Wang, Qi He, Ming Jin, Wei Jin

关键词：时空推理，空间感知RL，LLM

4 Traffic-R1: Reinforced LLMs Bring Human-Like Reasoning to Traffic Signal Control Systems

链接：https://aclanthology.org/2026.acl-long.995/

作者：Xingchen Zou, Yuhao Yang, Zheng Chen, Xixuan Hao, Yiqi chen, Chao Huang, Yuxuan Liang

关键词：信号灯控制，LLM

Traffic-R1：让红绿灯也会“思考”的通用信控大模型

5 TransLLM: A Unified Multi-Task Large Language Model for Urban Transportation via Learnable Prompting

链接：https://aclanthology.org/2026.acl-long.1195/

作者：Jiaming Leng, Yunying Bi, Chuan Qin, Zhenya Huang, Bing Yin, Haojie Ren, Yanyong Zhang, Chao Wang

关键词：城市交通，多任务,LLM

6 UrbanGeoEval: A City-Scale Benchmark for Evaluating Large Language Models in Geospatial Reasoning

链接：https://aclanthology.org/2026.acl-long.1867/

作者：Mutian Bao, Qiuyi Qi, Tian Liang, Jinjian Zhang, Wei Zhou, Ming Kong, Linjian Mo, Qiang Zhu

关键词：benchmark，地理空间推理

7 GCA Framework: A GCC Countries–Grounded Dataset and Agentic Pipeline for Climate Decision Support

链接：https://aclanthology.org/2026.acl-long.1967/

作者：Muhammad Umer Sheikh, Khawar shehzad, Salman Khan, Fahad Shahbaz Khan, Muhammad Haris Khan

关键词：气候决策支持，Agentic

8 Spatial-Agent: Agentic Geo-spatial Reasoning with Scientific Core Concepts

链接：https://aclanthology.org/2026.acl-long.679/

作者：Riyang Bao, Cheng Yang, Dazhou Yu, Zhexiang Tang, Gengchen Mai, Liang Zhao

关键词：空间Agent，地理空间推理

Spatial-Agent: 让 LLM Agent 从“会调地图 API”走向“会生成地理分析工作流”

Findings

9 Spatial-RAG: Spatial Retrieval Augmented Generation for Real-World Geospatial Reasoning Questions

链接：https://aclanthology.org/2026.findings-acl.539/

作者：Dazhou Yu, Riyang Bao, Ruiyu Ning, Jinghong Peng, Gengchen Mai, Liang Zhao

关键词：地理空间推理问题，空间-RAG

开启空间智能问答新时代：Spatial-RAG框架来了

10 ClimAgent: LLM as Agents for Autonomous Open-ended Climate Science Analysis

链接：https://aclanthology.org/2026.findings-acl.1067/

作者：Hao Wang, Jindong Han, Wei Fan, Hao Liu

关键词：气象Agent

11 ClimateCause: Complex and Implicit Causal Structures in Climate Reports

链接：https://aclanthology.org/2026.findings-acl.1272/

作者：Liesbeth Allein, Nataly Pineda-Castañeda, Andrea Rocci, Marie-Francine Moens

关键词：因果，气象报告

本文参与腾讯云自媒体同步曝光计划，分享自微信公众号。原始发表：2026-06-29，如有侵权请联系[email protected] 删除