Self-Evolving Multimedia Verification through Memory Consolidation of Contestation Experiences

2026-09-22

AI Summary

为解决多媒体验证中的准确性和可追溯性问题，提出SEMV框架，通过结合定量论辩、因果修正和记忆巩固等方法提高验证准确性并减少错误转移。

Abstract

Multimedia verification requires not only accurate decisions but also traceable evidence, reliable human correction, and safe reuse of prior experience. Existing systems often lack explicit mechanisms for revising intermediate reasoning or preventing harmful knowledge transfer. We present SEMV (Self-Evolving Multimedia Verification), a self-evolving multi-agent framework that treats provenance-bearing arguments as the interface between evidence, reasoning, human contestation, and memory. SEMV combines arena-based quantitative bipolar argumentation (A-QBAF), causal and scoped revision, and verification-gated memory consolidation with explicit conflict retention. On COSMOS benchmark, SEMV achieves 91.88% accuracy versus 89.10% for the strongest comparable baseline. Verified memory reduces negative transfer from 5.7% to 0.2%. On CTR benchmark, constructed from reviewer contestations, scoped causal revision corrects 96.7% of initial errors while saving 52.8% compute. MV2026 Grand Challenge dataset further supports evidence-grounded, temporally consistent reporting. These results show that SEMV can evolve through verified experience while keeping accumulated knowledge and subsequent decisions traceable, revisable, and contestable.

Problem

• Multimedia Verification
• Traceable Evidence
• Human Correction
• Knowledge Transfer

Innovation

• Self-Evolving Multimedia Verification
• A-QBAF
• causal and scoped revision
• verification-gated memory consolidation
• conflict retention