Agentic AI-Empowered Dynamic Survey Framework

2026-02-03

AI Summary

This work proposes a novel paradigm for dynamic, continuously evolving literature reviews by treating them as “living documents,” addressing the limitations of traditional static surveys that rapidly become outdated and contribute to knowledge fragmentation. The approach introduces the first framework for maintaining up-to-date reviews through an agent-driven AI system that integrates incremental learning with structure-aware fusion techniques. This enables automatic identification of emerging research and its coherent, structure-preserving incorporation into existing reviews. Retrospective experiments demonstrate that the framework effectively assimilates new literature while preserving logical coherence and the original organizational structure, thereby overcoming the constraints inherent in conventional one-time review generation.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Agent-Based Simulation and Emergent Behavior
• Machine Learning: Life-Long and Continual Learning

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Web Mining and Content Analysis: Models for Web evolution

Abstract

Survey papers play a central role in synthesizing and organizing scientific knowledge, yet they are increasingly strained by the rapid growth of research output. As new work continues to appear after publication, surveys quickly become outdated, contributing to redundancy and fragmentation in the literature. We reframe survey writing as a long-horizon maintenance problem rather than a one-time generation task, treating surveys as living documents that evolve alongside the research they describe. We propose an agentic Dynamic Survey Framework that supports the continuous updating of existing survey papers by incrementally integrating new work while preserving survey structure and minimizing unnecessary disruption. Using a retrospective experimental setup, we demonstrate that the proposed framework effectively identifies and incorporates emerging research while preserving the coherence and structure of existing surveys.

Problem

• survey papers
• knowledge synthesis
• research growth
• literature fragmentation
• outdated reviews

Innovation

• Agentic AI
• Dynamic Survey
• Living Document
• Incremental Integration
• Long-horizon Maintenance