Narrative Memory in Machines: Multi-Agent Arc Extraction in Serialized TV
By: Roberto Balestri, Guglielmo Pescatore
Potential Business Impact:
Helps computers understand TV show stories.
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.
Similar Papers
Multi-Agent System for AI-Assisted Extraction of Narrative Arcs in TV Series
Computation and Language
Tracks TV show stories to understand plot types.
Episodic Memory in Agentic Frameworks: Suggesting Next Tasks
Multiagent Systems
Helps AI remember past work to suggest new ideas.
Automated Clinical Problem Detection from SOAP Notes using a Collaborative Multi-Agent LLM Architecture
Artificial Intelligence
Helps doctors find sickness faster by teamwork.