Brief

Researchers have developed NewsLens, a novel five-agent framework designed to navigate and expose nuanced aspects of news bias beyond simple classification. This system utilizes a collaborative pipeline of agents, including fact verifiers and framing analysts, to deconstruct articles into interpretable framing maps. The framework aims to reveal ideological omissions and rhetorical manipulation, offering a more structured approach to understanding media bias. Evaluations using Qwen2.5-3B-Instruct and Mistral 7B models on geopolitical events indicate that center outlets exhibit higher perspective divergence, while conservative-framing outlets show greater manipulation. AI