EvoSpark: Endogenous Interactive Agent Societies for Unified Long-Horizon Narrative Evolution
Shiyu He, Minchi Kuang, Mengxian Wang, Bin Hu, and Tingxiang Gu

TL;DR
EvoSpark is a framework that enables long-horizon, coherent narrative evolution in multi-agent systems by employing memory, alignment mechanisms, and a unified engine to sustain story consistency.
Contribution
It introduces a novel architecture combining memory, alignment, and grounding protocols to maintain logical coherence in evolving narratives within agent societies.
Findings
EvoSpark outperforms baselines in generating coherent long-term narratives.
The framework effectively resolves conflicts and maintains spatial and relational consistency.
Experiments show sustained, expressive story evolution in diverse scenarios.
Abstract
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
