analiza aiqbench
This research introduces STReason, a framework that combines large language models with spatio-temporal analytics to handle complex, multi-task reasoning without requiring task-specific fine-tuning. By decomposing queries into executable programs and grounding outputs in verified computations, the system effectively mitigates hallucinations common in standard LLM approaches. The study establishes a new benchmark dataset and evaluation metrics specifically designed for long-form reasoning in dynamic data environments.
A Modular Multitask Reasoning Framework Integrating Spatio-temporal Models and LLMs
arXiv:2506.20073v2 Announce Type: replace 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 requires 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 task-specific fine-tuning, STReason leverages in-context learning to decompose complex natural language queries into modular, interpretable programs, which are then systematically executed to generate both numerical solutions and detailed reasoning rationales. By grounding all explanations in verified computational outputs, STReason inherently suppresses factual hallucinations common in direct-prompt LLM approaches. To enable 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 demonstrate that STReason significantly outperforms advanced LLM baselines across all reasoning 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.
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 requires 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 task-specific fine-tuning, STReason leverages in-context learning to decompose complex natural language queries into modular, interpretable programs, which are then systematically executed to generate both numerical solutions and detailed reasoning rationales. By grounding all explanations in verified computational outputs, STReason inherently suppresses factual hallucinations common in direct-prompt LLM approaches. To enable 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 demonstrate that STReason significantly outperforms advanced LLM baselines across all reasoning 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.
Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
arXiv:2506.20073 [cs.CL]
(or arXiv:2506.20073v2 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2506.20073 Focus to learn more arXiv-issued DOI via DataCite
https://doi.org/10.1145/3841645.3843050 Focus to learn more DOI(s) linking to related resources
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 308 cuvinte
Subiecte conexe
STRAND: Benchmarking and Improving Object-Centric Spatio-Temporal Monitoring in Video Large Language Models
arXiv · 25 sept. 2026
UniST-Pred: A Robust Unified Framework for Spatio-Temporal Traffic Forecasting in Transportation Networks Under Disruptions
arXiv · 1 oct. 2026
Robot-GST: geometry-aware spatial-temporal robot policy representation and evaluation
arXiv · 30 sept. 2026
Personalized and Robust Proactive Robot Assistance with Uncertainty-Guided LLM Reasoning
arXiv · 9 iun. 2026