A Modular Multitask Reasoning Framework Integrating Spatio-temporal Models and LLMs

TL;DR

STReason is a novel framework that combines large language models with spatio-temporal models to perform multi-task, long-form reasoning on complex data without task-specific fine-tuning, advancing the field of spatio-temporal data analysis.

Contribution

Introduces STReason, a modular, multi-task reasoning framework integrating LLMs with spatio-temporal models, enabling complex inference and explanations without fine-tuning.

Findings

Outperforms advanced LLM baselines across all metrics

Excels in complex, reasoning-intensive spatio-temporal scenarios

Validated by human evaluations showing practical utility

Abstract

Spatio-temporal data mining plays a pivotal role in informed decision making across diverse domains. However, existing models are often restricted to narrow tasks, lacking the capacity for multi-task inference and complex long-form reasoning that require generation of in-depth, explanatory outputs. These limitations restrict their applicability to real-world, multi-faceted decision scenarios. In this work, we introduce STReason, a novel framework that integrates the reasoning strengths of large language models (LLMs) with the analytical capabilities of spatio-temporal models for multi-task inference and execution. Without requiring task-specific finetuning, STReason leverages in-context learning to decompose complex natural language queries into modular, interpretable programs, which are then systematically executed to generate both solutions and detailed rationales. To facilitate rigorous evaluation, we construct a new benchmark dataset and propose a unified evaluation framework with metrics specifically designed for long-form spatio-temporal reasoning. Experimental results show that STReason significantly outperforms advanced LLM baselines across all metrics, particularly excelling in complex, reasoning-intensive spatio-temporal scenarios. Human evaluations further validate STReason's credibility and practical utility, demonstrating its potential to reduce expert workload and broaden the applicability to real-world spatio-temporal tasks. We believe STReason provides a promising direction for developing more capable and generalizable spatio-temporal reasoning systems.