Agenda-based Narrative Extraction: Steering Pathfinding Algorithms with Large Language Models

TL;DR

This paper introduces an agenda-based method that uses large language models to steer narrative pathfinding algorithms, enabling multi-perspective story extraction with high coherence and agenda alignment.

Contribution

It integrates LLMs into narrative pathfinding to guide storylines toward user-defined perspectives, balancing coherence and multi-storyline support.

Findings

LLM steering improves agenda alignment by 9.9% over keyword matching.

Minimal coherence loss of 2.2% compared to baseline.

Counter-agendas score low, confirming no fabrication of unsupported narratives.

Abstract

Existing narrative extraction methods face a trade-off between coherence, interactivity, and multi-storyline support. Narrative Maps supports rich interaction and generates multiple storylines as a byproduct of its coverage constraints, though this comes at the cost of individual path coherence. Narrative Trails achieves high coherence through maximum capacity path optimization but provides no mechanism for user guidance or multiple perspectives. We introduce agenda-based narrative extraction, a method that bridges this gap by integrating large language models into the Narrative Trails pathfinding process to steer storyline construction toward user-specified perspectives. Our approach uses an LLM at each step to rank candidate documents based on their alignment with a given agenda while maintaining narrative coherence. Running the algorithm with different agendas yields different storylines through the same corpus. We evaluated our approach on a news article corpus using LLM judges with Claude Opus 4.5 and GPT 5.1, measuring both coherence and agenda alignment across 64 endpoint pairs and 6 agendas. LLM-driven steering achieves 9.9% higher alignment than keyword matching on semantic agendas (p=0.017), with 13.3% improvement on \textit{Regime Crackdown} specifically (p=0.037), while keyword matching remains competitive on agendas with literal keyword overlap. The coherence cost is minimal: LLM steering reduces coherence by only 2.2% compared to the agenda-agnostic baseline. Counter-agendas that contradict the source material score uniformly low (2.2-2.5) across all methods, confirming that steering cannot fabricate unsupported narratives.