Narrative Memory in Machines: Multi-Agent Arc Extraction in Serialized TV

2025-08-09

AI Summary

To address the information management challenges arising from long temporal spans and interleaved plotlines in television drama narrative arc extraction, this paper proposes a memory-driven narrative understanding framework. Methodologically, it establishes a computational architecture inspired by human semantic, episodic, and working memory, integrating large language models, vector databases, and multi-agent coordination to identify and dynamically integrate narrative units from paratextual sources (e.g., episode summaries), while supporting human-in-the-loop refinement. Its key contribution lies in the first systematic application of hierarchical memory modeling to long-sequence narrative analysis. Evaluated on Season 1 of *Grey’s Anatomy*, the framework successfully identifies three distinct narrative arcs, accurately captures self-contained narrative units and character entity evolution, and demonstrates both effectiveness and interpretability in modeling complex, cross-temporal narrative structures.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Natural Language Processing: Information Extraction
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding
• Web Mining and Content Analysis: Models for Web evolution

Abstract

Serialized television narratives present significant analytical challenges due to their complex, temporally distributed storylines that necessitate sophisticated information management. This paper introduces a multi-agent system (MAS) designed to extract and analyze narrative arcs by implementing principles of computational memory architectures. The system conceptualizes narrative understanding through analogues of human memory: Large Language Models (LLMs) provide a form of semantic memory for general narrative patterns, while a vector database stores specific arc progressions as episodic memories. A multi-agent workflow simulates working memory processes to integrate these information types. Tested on the first season of Grey's Anatomy (ABC 2005-), the MAS identifies three arc types: Anthology (self-contained), Soap (relationship-focused), and Genre-Specific. These arcs and their episodic developments are stored in a vector database, facilitating structured analysis and semantic comparison. To bridge automation with critical interpretation, a graphical interface enables human oversight and refinement of the system's narrative memory. While demonstrating strong performance in identifying Anthology Arcs and character entities, the system's reliance on textual paratexts (episode summaries) revealed limitations in discerning overlapping arcs and opaque dynamics, underscoring the challenges in computational memory consolidation versus human holistic understanding. This memory-centric approach highlights the potential of combining AI-driven memory processing with human expertise. Beyond television, it offers promise for serialized written formats where narrative is entirely text-based. Future work will focus on integrating multimodal inputs to enrich episodic memory, refining memory integration mechanisms within the MAS, and expanding testing across diverse genres.

Problem

• Extracting complex narrative arcs from serialized TV shows
• Combining AI memory models with human oversight for analysis
• Addressing limitations in detecting overlapping and opaque storylines

Innovation

• Multi-agent system extracts narrative arcs
• LLMs and vector database simulate memory
• Graphical interface enables human oversight