AI RESEARCH
Through the Lens of Character: Resolving Modality-Role Interference in Multimodal Role-Playing Agent
arXiv CS.CV
•
ArXi:2605.09443v1 Announce Type: new The advancement of Multimodal Large Language Models (MLLMs) has expanded Role-Playing Agents (RPAs) into visually grounded environments. However, human vision is inherently subjective and identity-driven, whereas existing MLLMs extract objective, character-agnostic features for general tasks. In RPAs, this generic visual noise overpowers fragile character traits, causing Modality-Role Interference (MRI), where agents struggle to integrate visual grounding and character consistency. To address this, we