# EvoSpark: Endogenous Interactive Agent Societies for Unified Long-Horizon Narrative Evolution

arXiv: https://arxiv.org/abs/2604.12776 · HTML: https://mlsanity.com/paper/2604.12776/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use.
- Builds on 12 of its 22 references that are in the map.
- First posted on arXiv 14 Apr 2026.

## Placed in

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

## Builds on (most cited first, 12 of 12)

- [CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society](https://mlsanity.com/paper/2303.17760/) (2023)
- [Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents](https://mlsanity.com/paper/2505.22954/) (2025)
- [War and Peace (WarAgent): Large Language Model-based Multi-Agent Simulation of World Wars](https://mlsanity.com/paper/2311.17227/) (2023)
- [IBSEN: Director-Actor Agent Collaboration for Controllable and Interactive Drama Script Generation](https://mlsanity.com/paper/2407.01093/) (2024)
- [Generating Long-form Story Using Dynamic Hierarchical Outlining with Memory-Enhancement](https://mlsanity.com/paper/2412.13575/) (2024)
- [CoMAS: Co-Evolving Multi-Agent Systems via Interaction Rewards](https://mlsanity.com/paper/2510.08529/) (2025)
- [HoLLMwood: Unleashing the Creativity of Large Language Models in Screenwriting via Role Playing](https://mlsanity.com/paper/2406.11683/) (2024)
- [StoryVerse: Towards Co-authoring Dynamic Plot with LLM-based Character Simulation via Narrative Planning](https://mlsanity.com/paper/2405.13042/) (2024)
- [StoryWriter: A Multi-Agent Framework for Long Story Generation](https://mlsanity.com/paper/2506.16445/) (2025)
- [Drama Llama: An LLM-Powered Storylets Framework for Authorable Responsiveness in Interactive Narrative](https://mlsanity.com/paper/2501.09099/) (2025)
- [ID-RAG: Identity Retrieval-Augmented Generation for Long-Horizon Persona Coherence in Generative Agents](https://mlsanity.com/paper/2509.25299/) (2025)
- [OPEN-THEATRE: An Open-Source Toolkit for LLM-based Interactive Drama](https://mlsanity.com/paper/2509.16713/) (2025)

## Abstract (arXiv)

Realizing endogenous narrative evolution in LLM-based multi-agent systems is hindered by the inherent stochasticity of generative emergence. In particular, long-horizon simulations suffer from social memory stacking, where conflicting relational states accumulate without resolution, and narrative-spatial dissonance, where spatial logic detaches from the evolving plot. To bridge this gap, we propose EvoSpark, a framework specifically designed to sustain logically coherent long-horizon narratives within Endogenous Interactive Agent Societies. To ensure consistency, the Stratified Narrative Memory employs a Role Socio-Evolutionary Base as living cognition, dynamically metabolizing experiences to resolve historical conflicts. Complementarily, Generative Mise-en-Sc`ene mechanism enforces Role-Location-Plot alignment, synchronizing character presence with the narrative flow. Underpinning these is the Unified Narrative Operation Engine, which integrates an Emergent Character Grounding Protocol to transform stochastic sparking into persistent characters. This engine establishes a substrate that expands a minimal premise into an open-ended, evolving story world. Experiments demonstrate that EvoSpark significantly outperforms baselines across diverse paradigms, enabling the sustained generation of expressive and coherent narrative experiences.