From Personas to Plot: Character-Grounded Multi-Agent Story Generation for Long-Form Narratives
Although large language models (LLMs) have demonstrated impressive creative fiction generation, they struggle to maintain narrative consistency and coherent plot lines in long-form stories. In this work, we introduce a unified framework for long-form narrative generation and verification. MAGNET, a multi-agent goal-driven narrative engine for storytelling, generates stories with persona-grounded character agents that propose actions based on a shared world state and evolving story goals, while ATLAS is a graph-based pipeline that compares scene-level world representations across a generated st
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- FuzzySimilar title/name (fuzzy) · 59%AgentCore-8B →
“Fuzzy title match (0.73): “From Personas to Plot: Character-Grounded Multi-Agent Story ” ≈ “AgentCore-8B””
- PossiblePossibly related (embedding) · 52%grandgaming9321-prog/reality-engine →
- PossiblePossibly related (embedding) · 54%janaador0827-commits/simulacra-forge →
- PossiblePossibly related (embedding) · 54%unitagain/WenShape →
- PossiblePossibly related (embedding) · 49%lechmazur/writing →
- FuzzySimilar title/name (fuzzy) · 87%zhayujie/CowAgent →
“Fuzzy title match (0.94): “From Personas to Plot: Character-Grounded Multi-Agent Story ” ≈ “zhayujie/CowAgent””
- FuzzySimilar title/name (fuzzy) · 66%open-multi-agent/open-multi-agent →
“Fuzzy title match (0.78): “From Personas to Plot: Character-Grounded Multi-Agent Story ” ≈ “open-multi-agent/open-multi-agent””
- FuzzySimilar title/name (fuzzy) · 59%NousResearch/hermes-agent →
“Fuzzy title match (0.73): “From Personas to Plot: Character-Grounded Multi-Agent Story ” ≈ “NousResearch/hermes-agent””