arXiv cs.MA· Ilyas Nagiyev, Miras Baisbay, Daniil Orel, Preslav Nakov·· 11 小时前AI 评分34
SCOPE：面向新闻媒体偏见与可信度评估的多智能体系统
SCOPE: Source Credibility and Outlet Profiling Engine
AI 导读
SCOPE 是一个多智能体系统，输入媒体机构 URL 后协调文章抓取、内容分析、外部证据检索、评分与报告生成等专用智能体，按 MBFC 式方法对媒体的偏见、事实性与可信度进行画像。在 200 家媒体的基准测试中，SCOPE 在多数指标上优于纯 LLM、纯文章、纯搜索和媒体背景调查基线，取得最低的偏见与事实性 MAE、完美的失败事实核查检出率以及最低的事实错误率。代码与在线演示均已公开。
正文
Abstract:We present SCOPE, a multi-agent system for profiling news media outlets with respect to bias, factuality, and credibility. Given an outlet URL, SCOPE coordinates specialized agents for article acquisition, content analysis, external evidence search, scoring, and report generation. The system follows an MBFC-style methodology while making intermediate evidence and agent outputs inspectable through a structured demonstration interface. On a benchmark of 200 media outlets, SCOPE outperforms LLM-only, article-only, search-only, and media-background-check baselines on most metrics, achieving the lowest bias and factuality MAE, perfect failed-fact-check detection, and the lowest factual error rate. These results suggest that decomposed, evidence-grounded agent workflows can support more transparent and reliable media profiling. Our code is available at this https URL, and a live demonstration at this https URL.
| Subjects: | Multiagent Systems (cs.MA); Artificial Intelligence (cs.AI); Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.35929 [cs.MA] |
| (or arXiv:2610.35929v1 [cs.MA] for this version) | |
| https://doi.org/10.48550/arXiv.2610.35929 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Daniil Orel Orel [view email]
[v1]
Sun, 18 Oct 2026 11:22:14 UTC (2,956 KB)
来源：arXiv cs.MA · arxiv.org