How can AI agents support journalists' work? An experiment with designing an LLM-driven intelligent reporting system

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Maltezos, Vasileios, Kyrychenko, Roman, Knuutila, Aleksi
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918152576696320
author Maltezos, Vasileios
Kyrychenko, Roman
Knuutila, Aleksi
author_facet Maltezos, Vasileios
Kyrychenko, Roman
Knuutila, Aleksi
contents The integration of artificial intelligence into journalistic practices represents a transformative shift in how news is gathered, analyzed, and disseminated. Large language models (LLMs), particularly those with agentic capabilities, offer unprecedented opportunities for enhancing journalistic workflows while simultaneously presenting complex challenges for newsroom integration. This research explores how agentic LLMs can support journalists' workflows, based on insights from journalist interviews and from the development of an LLM-based automation tool performing information filtering, summarization, and reporting. The paper details automated aggregation and summarization systems for journalists, presents a technical overview and evaluation of a user-centric LLM-driven reporting system (TeleFlash), and discusses both addressed and unmet journalist needs, with an outlook on future directions for AI-driven tools in journalism.
format Preprint
id arxiv_https___arxiv_org_abs_2510_01193
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle How can AI agents support journalists' work? An experiment with designing an LLM-driven intelligent reporting system
Maltezos, Vasileios
Kyrychenko, Roman
Knuutila, Aleksi
Human-Computer Interaction
Computers and Society
68T50
I.2; I.7; H.4; K.4; J.4
The integration of artificial intelligence into journalistic practices represents a transformative shift in how news is gathered, analyzed, and disseminated. Large language models (LLMs), particularly those with agentic capabilities, offer unprecedented opportunities for enhancing journalistic workflows while simultaneously presenting complex challenges for newsroom integration. This research explores how agentic LLMs can support journalists' workflows, based on insights from journalist interviews and from the development of an LLM-based automation tool performing information filtering, summarization, and reporting. The paper details automated aggregation and summarization systems for journalists, presents a technical overview and evaluation of a user-centric LLM-driven reporting system (TeleFlash), and discusses both addressed and unmet journalist needs, with an outlook on future directions for AI-driven tools in journalism.
title How can AI agents support journalists' work? An experiment with designing an LLM-driven intelligent reporting system
topic Human-Computer Interaction
Computers and Society
68T50
I.2; I.7; H.4; K.4; J.4
url https://arxiv.org/abs/2510.01193