IA-RAG: Interval-Algebra-Driven Temporal Reasoning for Dynamic Knowledge Retrieval

2026-06-04

AI Summary

This work addresses the limitation of existing retrieval-augmented generation (RAG) approaches in modeling the temporal dynamics of knowledge, particularly their inability to capture fine-grained temporal relations such as duration, overlap, and containment among events. To overcome this, the authors propose a hierarchical RAG framework grounded in temporal intervals, which integrates Allen’s interval algebra into the RAG architecture for the first time. Facts are represented as Interval-based Event Units (IEUs), and a thematic forest structure is introduced to organize and reason over knowledge under formal temporal constraints. A subgraph temporal tightening mechanism is further devised to handle ambiguous temporal boundaries, enabling joint retrieval of both explicit and implicit temporal semantics. The method achieves substantial performance gains over state-of-the-art baselines on temporal question answering benchmarks—including TimeQA, TempReason, and ComplexTR—with especially strong results on complex compositional temporal reasoning tasks.

Abstract

Retrieval-Augmented Generation (RAG) has shown strong effectiveness in grounding Large Language Models (LLMs) with external knowledge. However, existing RAG and Graph RAG frameworks largely treat knowledge as static or associate time with coarse-grained timestamps or metadata, failing to capture rich temporal structures such as duration, overlap, and containment. We propose IA-RAG, a hierarchical temporal RAG framework that models knowledge as time intervals and performs retrieval under formal temporal constraints. IA-RAG represents facts as Interval Event Units (IEUs) and organizes them into a hierarchical Thematic Forest, where temporal dependencies are governed by Allen's Interval Algebra. To handle incomplete or uncertain temporal boundaries, IA-RAG further introduces a Sub-graph Time Tightening mechanism that refines fuzzy intervals through logical constraints within connected event subgraphs. In addition, IA-RAG supports implicit temporal semantic retrieval through interval-algebra-guided traversal. Experiments on multiple temporal question answering benchmarks, including TimeQA, TempReason, and ComplexTR, demonstrate that IA-RAG achieves strong temporal retrieval and reasoning performance, particularly on complex compositional temporal reasoning tasks. Our code is released at https://github.com/xiaoAugenstern/LogicalRAG_TemporalQA.

Problem

• Temporal Reasoning
• Retrieval-Augmented Generation
• Interval Algebra
• Dynamic Knowledge Retrieval
• Temporal Structure

Innovation

• Interval Algebra
• Temporal Reasoning
• Retrieval-Augmented Generation
• Time Interval Modeling
• Hierarchical Knowledge Organization