AdapTime: Enabling Adaptive Temporal Reasoning in Large Language Models

2026-04-27

AI Summary

This work addresses the limited capability and poor generalization of large language models (LLMs) in temporal reasoning tasks, as well as the rigidity of existing approaches that rely on fixed reasoning pipelines ill-suited for problems of varying complexity. To overcome these limitations, we propose AdapTime, an adaptive temporal reasoning framework that dynamically selects reasoning strategies based on input context—a first in this domain. AdapTime employs an LLM as a planner to flexibly orchestrate three core reasoning actions: restatement, reformulation, and verification. This design avoids both over-processing of simple queries and under-reasoning on complex ones, all while operating without external tools and integrating seamlessly into mainstream LLMs. Experimental results demonstrate that AdapTime substantially enhances temporal reasoning performance, achieving both high efficiency and broad applicability.

Technology Category

• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Planning, Routing, and Scheduling: Temporal Planning
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Large language models for search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Large language models have demonstrated strong reasoning capabilities in general knowledge question answering. However, their ability to handle temporal information remains limited. To address this limitation, existing approaches often involve external tools or manual verification and are tailored to specific scenarios, leading to poor generalizability. Moreover, these methods apply a fixed pipeline to all questions, overlooking the fact that different types of temporal questions require distinct reasoning strategies, which leads to unnecessary processing for simple cases and inadequate reasoning for complex ones. To this end, we propose AdapTime, an adaptive temporal reasoning method that dynamically executes reasoning steps based on the input context. Specifically, it involves three temporal reasoning actions: reformulate, rewrite and review, with an LLM planner guiding the reasoning process. AdapTime integrates seamlessly with state-of-the-art LLMs and significantly enhances their temporal reasoning capabilities without relying on external support. Extensive experiments demonstrate the effectiveness of our approach.

Problem

• temporal reasoning
• large language models
• adaptive reasoning
• time-aware question answering
• reasoning generalizability

Innovation

• adaptive temporal reasoning
• large language models
• dynamic reasoning
• temporal question answering
• LLM planner