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

arXiv: https://arxiv.org/abs/2508.07010 · HTML: https://mlsanity.com/paper/2508.07010/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use.
- Builds on 14 of its 49 references that are in the map.
- First posted on arXiv 9 Aug 2025.

## Placed in

- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 14 of 14)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Recent Trends in Deep Learning Based Natural Language Processing](https://mlsanity.com/paper/1708.02709/) (2017)
- [SciAgents: Automating scientific discovery through multi-agent intelligent graph reasoning](https://mlsanity.com/paper/2409.05556/) (2024)
- [Comparative Study of CNN and RNN for Natural Language Processing](https://mlsanity.com/paper/1702.01923/) (2017)
- [The emotional arcs of stories are dominated by six basic shapes](https://mlsanity.com/paper/1606.07772/) (2016)
- [M+: Extending MemoryLLM with Scalable Long-Term Memory](https://mlsanity.com/paper/2502.00592/) (2025)
- [Modelling Suspense in Short Stories as Uncertainty Reduction over Neural Representation](https://mlsanity.com/paper/2004.14905/) (2020)
- [Can Large Language Models Grasp Legal Theories? Enhance Legal Reasoning with Insights from Multi-Agent Collaboration](https://mlsanity.com/paper/2410.02507/) (2024)
- [Mapping Out Narrative Structures and Dynamics Using Networks and Textual Information](https://mlsanity.com/paper/1604.03029/) (2016)
- [Narrative Smoothing: Dynamic Conversational Network for the Analysis of TV Series Plots](https://mlsanity.com/paper/1602.07811/) (2016)
- [Balance of thrones: a network study on Game of Thrones](https://mlsanity.com/paper/1707.05213/) (2017)
- [Network Science Predicts Who Dies Next in Game of Thrones](https://mlsanity.com/paper/2110.09856/) (2021)
- [Multi-Agent System for AI-Assisted Extraction of Narrative Arcs in TV Series](https://mlsanity.com/paper/2503.04817/) (2025)

## Built on by (most cited first, 1 of 1)

- [From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanisms](https://mlsanity.com/paper/2605.06716/) (2026)

## Abstract (arXiv)

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.