Metraipolis › archive › dc_8a110fcc4890

Self-Evolving Multimedia Verification through Memory Consolidation of Contestation Experiences — arXiv:2609.27175

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.27175
License (as archived): CC0-1.0
Archived: 2026-10-08T08:57:24.424Z
SHA-256 of the archived text: 62cf0b55316a1a46b9a8dea3099785788a0fd794e2576e9be6307b20f9d9e153
Stable URL of this page: https://metraipolis.com/documento/dc_8a110fcc4890

How to cite

Self-Evolving Multimedia Verification through Memory Consolidation of Contestation Experiences — arXiv:2609.27175 — arXiv (en), https://arxiv.org/abs/2609.27175 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8a110fcc4890 (Metraipolis archive dc_8a110fcc4890, sha256 62cf0b55316a1a46b9a8dea3099785788a0fd794e2576e9be6307b20f9d9e153)

BibTeX

@misc{dc8a110fcc4890,
  title = {Self-Evolving Multimedia Verification through Memory Consolidation of Contestation Experiences — arXiv:2609.27175},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.27175},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8a110fcc4890; sha256 62cf0b55316a1a46b9a8dea3099785788a0fd794e2576e9be6307b20f9d9e153},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.27175. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-24 in cs.MA).
Categorie arXiv: Multimedia (cs.MM) ; Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA).
Pagina del lavoro: https://arxiv.org/abs/2609.27175 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-08T08:03:18.942Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-09-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).